© 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. 41823
    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
    ervers
    -0.26
    .lab
    -0.25
    feld
    -0.25
    éĺµ
    -0.25
    ç¼Ļ
    -0.25
    ystack
    -0.25
    .field
    -0.25
     labelText
    -0.24
    à¸Ńะà¹Ħร
    -0.24
    даваÑĤÑĮ
    -0.24
    POSITIVE LOGITS
    å²ij
    0.31
    oodle
    0.27
    ine
    0.27
    票
    0.26
    èĭ·
    0.26
    ool
    0.26
    SqlServer
    0.25
    åįĬ
    0.25
    Merit
    0.25
    unic
    0.25
    Activations Density 0.000%

    No Known Activations