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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    11. 8690
    Prev
    Next
    INDEX
    Explanations

    Go programming and web addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uddle
    -0.07
    grese
    -0.07
    这样做
    -0.07
    لو
    -0.07
    歌舞
    -0.07
     Mare
    -0.07
    atology
    -0.07
     dismissing
    -0.06
    nce
    -0.06
    登錄
    -0.06
    POSITIVE LOGITS
    日渐
    0.08
    .FileOutputStream
    0.07
    嬖
    0.07
    Extra
    0.06
    チェ
    0.06
     consistently
    0.06
     synthetic
    0.06
    突如其来
    0.06
     pores
    0.06
    .ObjectMeta
    0.06
    Activations Density 0.024%

    No Known Activations