© 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. 39940
    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
    BorderStyle
    -0.34
    .dds
    -0.27
     timedelta
    -0.25
    Exactly
    -0.25
    ToFit
    -0.24
    æŃ£å¸¸ä½¿çĶ¨
    -0.24
    èĦ²
    -0.24
    ypy
    -0.24
     coli
    -0.24
     Maver
    -0.24
    POSITIVE LOGITS
    çĽĬ
    0.32
    å¯ĵ
    0.27
    hist
    0.27
     sme
    0.26
    iento
    0.25
    aler
    0.25
    stay
    0.25
    match
    0.24
    dens
    0.24
     ENG
    0.24
    Activations Density 1.003%

    No Known Activations

    This feature has no known activations.