© 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. 40630
    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
    pora
    -0.28
    worth
    -0.28
    buah
    -0.28
    enção
    -0.26
     pragma
    -0.26
    ä¸Ģæīĭ
    -0.25
    @hotmail
    -0.25
    ophone
    -0.24
    avian
    -0.24
    ooth
    -0.24
    POSITIVE LOGITS
    笼
    0.27
     mills
    0.25
    _elems
    0.25
    ĤŃ
    0.23
    Ñĩе
    0.23
    çļĦæ¦Ĥ念
    0.23
    unda
    0.23
    _elements
    0.23
    _pa
    0.22
    赶
    0.22
    Activations Density 31.219%

    No Known Activations

    This feature has no known activations.