© 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. 12-TRANSCODER-HP
    7. 23568
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿ħä¸įåı¯
    -0.28
     legend
    -0.28
    .Team
    -0.27
    (DE
    -0.26
     Lon
    -0.25
     contr
    -0.25
    æŶæĬ¥
    -0.24
    lections
    -0.24
    lection
    -0.24
    tober
    -0.24
    POSITIVE LOGITS
    iku
    0.29
    ouse
    0.28
     gsi
    0.26
    amen
    0.26
    uis
    0.25
    ofile
    0.25
    OwnProperty
    0.24
     coinc
    0.24
    aji
    0.24
    iphy
    0.24
    Activations Density 0.016%

    No Known Activations