© 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 EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 8908
    Prev
    Next
    INDEX
    Explanations

    origin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DHCP
    -0.07
    ég
    -0.07
    .inc
    -0.06
     Proc
    -0.06
    uesday
    -0.06
    纯洁
    -0.06
    ))"↵
    -0.06
     tec
    -0.06
    (buff
    -0.06
    ☼
    -0.06
    POSITIVE LOGITS
     רבה
    0.08
    organisation
    0.07
    .power
    0.07
     же
    0.07
    自来水
    0.07
    كورون
    0.07
     jit
    0.07
    WM
    0.06
     replacement
    0.06
    ระบ
    0.06
    Activations Density 0.051%

    No Known Activations