© 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. 22500
    Prev
    Next
    INDEX
    Explanations

    Article beginnings

    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
    ä¸Ģå¤ľ
    -0.28
    charts
    -0.28
    orst
    -0.27
    åĩłå¼ł
    -0.26
    æ¶İ
    -0.26
     construed
    -0.26
    楹
    -0.25
    eyed
    -0.25
    ekyll
    -0.25
    stag
    -0.25
    POSITIVE LOGITS
    .addTo
    0.27
    ä¸įå¤ļ
    0.27
    ä¸ĭæĸ¹
    0.26
    tec
    0.26
    ãĤµãĥ¼ãĥĵ
    0.26
     subtract
    0.25
    åIJijä¸ĭ
    0.25
    tem
    0.25
    eps
    0.25
    æħ¢
    0.25
    Activations Density 0.000%

    No Known Activations