© 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. 40522
    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
     routinely
    -0.25
    ECH
    -0.24
    ãĢģãĢĮ
    -0.23
     xnxx
    -0.23
     duly
    -0.23
     personally
    -0.23
     ordinarily
    -0.23
    ä¾ĭè¡Į
    -0.22
     successfully
    -0.22
     publicly
    -0.22
    POSITIVE LOGITS
    -sided
    0.26
    æ¹ĥ
    0.26
    cri
    0.24
    -pad
    0.24
    _possible
    0.24
    trace
    0.23
     má»ĩnh
    0.23
     обоÑĢ
    0.23
    à¤Ń
    0.22
    erring
    0.22
    Activations Density 0.311%

    No Known Activations

    This feature has no known activations.