© 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. 32-TRANSCODER-HP
    7. 42182
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    论
    -0.27
    .edu
    -0.26
    她们
    -0.25
     bloodstream
    -0.25
    aso
    -0.24
     Punch
    -0.24
    åıijå±ķ空éĹ´
    -0.23
    èħ¥
    -0.23
    äºī论
    -0.23
     Dias
    -0.23
    POSITIVE LOGITS
    çĩŁ
    0.27
    awan
    0.27
    ç®Ģæ´ģ
    0.26
    梯
    0.25
     Ne
    0.23
    ä¸Ģæīĭ
    0.23
    .getContext
    0.23
    éĽª
    0.23
    ree
    0.23
    å§Ķç»Ħç»ĩ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.