© 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. 30-TRANSCODER-HP
    7. 96134
    Prev
    Next
    INDEX
    Explanations

    cooking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nex
    -0.27
    è¿Ľ
    -0.26
    opers
    -0.25
    onn
    -0.25
    unar
    -0.24
    è¿ĽäºĨ
    -0.24
     PROP
    -0.24
    çı
    -0.24
    kı
    -0.24
    ench
    -0.24
    POSITIVE LOGITS
     correctly
    0.35
    —which
    0.33
     which
    0.33
     peacefully
    0.32
    ,
    0.32
     differently
    0.31
     -
    0.30
     —
    0.30
     during
    0.29
    ï¼Įåľ¨
    0.29
    Activations Density 0.969%

    No Known Activations