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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 127178
    Prev
    Next
    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash

    instances of yes/no question phrasing (asking whether something is true).

    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
    -star
    -0.07
    램
    -0.07
    脂
    -0.07
     luz
    -0.07
    .mainloop
    -0.07
    袄
    -0.07
     Halo
    -0.06
    hält
    -0.06
    售后
    -0.06
     stylist
    -0.06
    POSITIVE LOGITS
    VECTOR
    0.07
    ceans
    0.07
    ','');↵
    0.07
    PCS
    0.07
    .Fprintf
    0.07
    上来
    0.07
     verbally
    0.07
     bpy
    0.06
    追究
    0.06
     rawData
    0.06
    Activations Density 0.171%

    No Known Activations