© 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. 39683
    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
     tails
    -0.27
    tails
    -0.26
    [](
    -0.25
    hatt
    -0.25
    tra
    -0.24
     cones
    -0.24
     goodies
    -0.24
    èµ°å¾Ĺ
    -0.24
    èĢģå¸ĪçļĦ
    -0.24
     ConcurrentHashMap
    -0.23
    POSITIVE LOGITS
    yny
    0.30
    çĸijéĹ®
    0.28
    .encoding
    0.27
    exercise
    0.26
    лик
    0.26
    éĵ¨
    0.25
    .band
    0.25
    ainment
    0.25
    裱
    0.24
     Himself
    0.24
    Activations Density 53.344%

    No Known Activations

    This feature has no known activations.