© 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. 40261
    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
    -hot
    -0.29
    çıĻ
    -0.27
    ãĥĻãĥ³
    -0.26
    ÅĤow
    -0.26
    éĻIJ度
    -0.25
     ath
    -0.25
    ng
    -0.25
    羣
    -0.24
     å½
    -0.24
    à¸ķาย
    -0.24
    POSITIVE LOGITS
    夫
    0.27
    çļĦç²¾ç¥ŀ
    0.26
    ichel
    0.25
     twink
    0.25
    èĭĵ
    0.25
    wares
    0.24
    åĨ³å®ļäºĨ
    0.23
    读åIJİæĦŁ
    0.23
    wear
    0.23
    inking
    0.23
    Activations Density 41.685%

    No Known Activations

    This feature has no known activations.