© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39879
    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
    obl
    -0.25
    ogne
    -0.24
     owed
    -0.23
    dialogs
    -0.23
     KV
    -0.23
    å®Į
    -0.23
    ?>"
    -0.23
    å¼ĢåıijèĢħ
    -0.23
    ç´¯äºĨ
    -0.22
    gom
    -0.22
    POSITIVE LOGITS
    H
    0.30
    0.28
     (
    0.27
     methods
    0.26
     H
    0.26
     T
    0.26
     Tor
    0.24
    on
    0.24
    lim
    0.24
    æµĵ
    0.24
    Activations Density 3.770%

    No Known Activations

    This feature has no known activations.