© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 115285
    Prev
    Next
    INDEX
    Explanations

    for

    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
    Negative Logits
    魔龙令牌
    -0.08
     เมษายน
    -0.07
     ceremony
    -0.07
     Poverty
    -0.07
     gridSize
    -0.07
     через
    -0.07
    胳膊
    -0.07
    𝗕
    -0.07
     bone
    -0.07
    打进
    -0.07
    POSITIVE LOGITS
    榕
    0.07
    ፊ
    0.07
     deployed
    0.07
    疳
    0.06
    轪
    0.06
    MakeRange
    0.06
    _SOL
    0.06
    _station
    0.06
    參考
    0.06
    ▚
    0.06
    Activations Density 0.020%

    No Known Activations