© 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. 42675
    Prev
    Next
    INDEX
    Explanations

    PubMed

    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
    _views
    -0.28
    INGTON
    -0.27
    ä¸įç»ı
    -0.27
    ACY
    -0.26
     troch
    -0.25
    rafted
    -0.24
    oland
    -0.24
     prospects
    -0.24
    ashes
    -0.24
    .digest
    -0.23
    POSITIVE LOGITS
    Nu
    0.30
    pm
    0.29
    PM
    0.29
    enna
    0.29
    HP
    0.29
    %p
    0.28
    ps
    0.28
    Hu
    0.28
    HR
    0.28
    HI
    0.27
    Activations Density 0.023%

    No Known Activations