© 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. 40632
    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
    char
    -0.29
    åĮº
    -0.28
    ç¾İ
    -0.28
    vin
    -0.27
    çĶ¨
    -0.27
    åħ¥
    -0.27
    ven
    -0.26
     char
    -0.26
    8
    -0.25
    符åIJĪ
    -0.25
    POSITIVE LOGITS
    åĬłçĽŁåºĹ
    0.28
    мед
    0.26
    é«ij
    0.25
     pouring
    0.25
    IMS
    0.25
    á»Ĵ
    0.25
    modx
    0.25
    lift
    0.24
    ]]></
    0.24
    Reviewer
    0.24
    Activations Density 1.499%

    No Known Activations

    This feature has no known activations.