© 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. 39036
    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
    é¦Ħ
    -0.29
     separate
    -0.29
     hans
    -0.28
     answers
    -0.27
     civilized
    -0.27
     settled
    -0.27
     optimized
    -0.27
     different
    -0.26
    åIJĦ家
    -0.26
     enlightened
    -0.26
    POSITIVE LOGITS
    æĬ¼
    0.30
     phẩm
    0.27
     réuss
    0.27
    éĢĨåĬ¿
    0.27
     srand
    0.26
     Attempt
    0.26
    åİĭåĪ¶
    0.26
    æ½ľèĥ½
    0.26
    undef
    0.25
    érica
    0.25
    Activations Density 23.755%

    No Known Activations

    This feature has no known activations.