© 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. 43482
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    np_max-act-logits · gemini-2.0-flash
    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
    ìļķ
    -0.30
     Blow
    -0.28
     blow
    -0.25
     Prest
    -0.25
    éĶħ
    -0.25
     olig
    -0.24
     flo
    -0.24
    erness
    -0.24
    olio
    -0.24
     Oliver
    -0.24
    POSITIVE LOGITS
    nas
    0.29
    xaf
    0.28
    å©Ĩ
    0.28
    alis
    0.27
    å³»
    0.26
    dsa
    0.25
     infinitely
    0.25
    å·¥ä½ľæĬ¥åijĬ
    0.24
    xdf
    0.24
    NAS
    0.24
    Activations Density 0.011%

    No Known Activations