© 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. 19-RESID-POST-AA
    11. 3120
    Prev
    Next
    INDEX
    Explanations

    Long strings of "="

    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
     niños
    -0.08
     pione
    -0.08
     kullanıcı
    -0.07
     Lakers
    -0.07
     bons
    -0.07
     getNode
    -0.07
    旋律
    -0.07
    mı
    -0.06
    🐿
    -0.06
    amarin
    -0.06
    POSITIVE LOGITS
    非法
    0.07
     submodule
    0.07
    同一
    0.06
    成立
    0.06
    '])↵↵
    0.06
     ').
    0.06
    ชาย
    0.06
     Lith
    0.06
    ALLOW
    0.06
    事实
    0.06
    Activations Density 0.000%

    No Known Activations