© 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. 23257
    Prev
    Next
    INDEX
    Explanations

    inflammation

    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
    typings
    -0.25
    .onCreate
    -0.24
    åı¸é©¬
    -0.24
    ÑĢе
    -0.24
    ä½ĵéªĮ
    -0.24
    æīĭ
    -0.24
    èĥ¶
    -0.24
    <AM
    -0.23
    ifact
    -0.23
     Patch
    -0.23
    POSITIVE LOGITS
    /mit
    0.28
     :)↵↵
    0.28
     :)↵
    0.27
    igan
    0.27
    igu
    0.26
    ä¸ĢåŃĹ
    0.25
    antan
    0.25
    gger
    0.25
    ä¾£
    0.25
    塾
    0.25
    Activations Density 0.000%

    No Known Activations