© 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. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    足
    -0.30
    >;č↵
    -0.29
    è½»
    -0.28
    çļĦæľĭåıĭ
    -0.26
    },č↵č↵
    -0.26
    };č↵č↵
    -0.26
    @↵↵
    -0.26
     Petr
    -0.25
     Dra
    -0.25
    å¯Ŀ
    -0.25
    POSITIVE LOGITS
    affer
    0.29
    rende
    0.28
    owered
    0.26
    cura
    0.26
    uges
    0.26
    accepted
    0.25
    çľ¼ä¸Ń
    0.25
    çľ¼ç¥ŀ
    0.25
    iren
    0.25
    ession
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.