© 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. 14-TRANSCODER-HP
    7. 40143
    Prev
    Next
    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Redemption
    -0.28
    ardi
    -0.27
    身边çļĦ
    -0.27
    绾
    -0.25
    usement
    -0.25
    napshot
    -0.24
    身边
    -0.24
    ount
    -0.23
    æĮģæľī人
    -0.23
    çij·
    -0.23
    POSITIVE LOGITS
    istrate
    0.28
     down
    0.28
    ä¸ĭæĿ¥
    0.26
    主导
    0.25
    Down
    0.25
     lightly
    0.25
    å®īåİ¿
    0.24
     kidding
    0.24
     Against
    0.24
    down
    0.24
    Activations Density 0.836%

    No Known Activations