© 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. 38745
    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
    ilar
    -0.32
    uros
    -0.28
    anka
    -0.27
    igar
    -0.27
    eway
    -0.27
    orean
    -0.27
    ennen
    -0.26
    ilers
    -0.26
    ossip
    -0.26
    ONS
    -0.26
    POSITIVE LOGITS
    çĵ¶
    0.26
    __(
    0.26
    åIJĮæŶ
    0.25
    prim
    0.25
    åĨµä¸Ķ
    0.25
    pac
    0.25
    åİŁåĪĻä¸Ĭ
    0.25
    ä¸īåĪĨ
    0.24
    åIJĮæĹ¶ä¹Łæĺ¯
    0.24
    pred
    0.24
    Activations Density 1.807%

    No Known Activations

    This feature has no known activations.