© 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. 31-TRANSCODER-HP
    7. 18595
    Prev
    Next
    INDEX
    Explanations

    phy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ent
    -0.28
     Star
    -0.27
     left
    -0.26
     Wash
    -0.26
    纹
    -0.25
    bus
    -0.25
     chill
    -0.25
    ãĥģãĥ£
    -0.24
    ISM
    -0.24
    éric
    -0.24
    POSITIVE LOGITS
    dap
    0.29
    aed
    0.25
    oge
    0.25
    æĹ¶è¡¨ç¤º
    0.24
    spo
    0.24
    oogle
    0.24
    Spe
    0.24
    åĩºèº«
    0.24
    ä¸įè´Ł
    0.24
    plies
    0.24
    Activations Density 0.019%

    No Known Activations