© 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. 38768
    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
    assed
    -0.28
    .names
    -0.28
    Trou
    -0.28
    iid
    -0.27
     trouble
    -0.27
    onnen
    -0.26
    SelectionMode
    -0.26
    elihood
    -0.25
    IID
    -0.25
    zia
    -0.25
    POSITIVE LOGITS
    æ¡©
    0.29
    åħį
    0.28
    oster
    0.26
    sth
    0.26
    详
    0.25
    没æľī
    0.25
    è·Ŀ离
    0.25
    èĮĤ
    0.25
    åįĵ
    0.25
     vz
    0.24
    Activations Density 15.026%

    No Known Activations

    This feature has no known activations.