© 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. 39896
    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
     died
    -0.25
     ÑĤоÑĢ
    -0.24
     centers
    -0.24
     nodded
    -0.24
     Poster
    -0.24
    åĿļæĮģ以
    -0.24
     geometry
    -0.24
     rotate
    -0.24
    Donate
    -0.24
    Poster
    -0.23
    POSITIVE LOGITS
    XS
    0.32
    WW
    0.29
    conf
    0.29
    TX
    0.26
    NX
    0.26
    ucch
    0.25
    GG
    0.25
    èģĮæĿĥ
    0.25
    cap
    0.25
    apore
    0.24
    Activations Density 0.061%

    No Known Activations

    This feature has no known activations.