© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79055
    Prev
    Next
    INDEX
    Explanations

    Nigerian scams

    np_max-act · gemini-2.0-flash

    Text characteristic of advance-fee/inheritance email scams — fraudulent solicitation messages requesting help/assistance to transfer money.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    不幸
    -0.08
    𝑵
    -0.07
    jom
    -0.07
     đô
    -0.07
    ı
    -0.07
    verb
    -0.07
    :mm
    -0.07
     пре
    -0.07
    шен
    -0.06
    确切
    -0.06
    POSITIVE LOGITS
    海拔
    0.07
    !--
    0.07
    徒弟
    0.06
     Millennials
    0.06
    混沌
    0.06
     erotici
    0.06
     yellow
    0.06
    花开
    0.06
     swearing
    0.06
    ڷ
    0.06
    Activations Density 0.029%

    No Known Activations