© 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. 38843
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Conduct
    -0.29
    GV
    -0.24
    åį±
    -0.24
    otr
    -0.24
    èµ°è¿ĩ
    -0.24
    é¹ij
    -0.24
    åIJİæŀľ
    -0.24
     PLAY
    -0.24
    éŀŃ
    -0.24
     COVER
    -0.24
    POSITIVE LOGITS
    ros
    0.27
    sets
    0.27
    -stack
    0.26
    repeat
    0.25
    lymp
    0.25
    answer
    0.24
    work
    0.24
    crate
    0.24
    sheets
    0.24
    scale
    0.24
    Activations Density 4.290%

    No Known Activations

    This feature has no known activations.