© 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. 38869
    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
    åĸ§
    -0.25
    缮ãģ«
    -0.25
    ÑĪки
    -0.24
    site
    -0.24
     suppress
    -0.24
     validations
    -0.24
    æŃī
    -0.23
     Prä
    -0.23
     Cros
    -0.23
    åīģ
    -0.23
    POSITIVE LOGITS
     nominate
    0.27
    åı¤ä»£
    0.26
    lege
    0.26
    æĹı
    0.25
     дол
    0.25
    å¹³åİŁ
    0.24
    %i
    0.24
     libertine
    0.24
     lobster
    0.23
    OrDefault
    0.23
    Activations Density 0.037%

    No Known Activations

    This feature has no known activations.