© 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. 25-TRANSCODER-HP
    7. 107788
    Prev
    Next
    INDEX
    Explanations

    how

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅĪ
    -0.27
    çĥ¨
    -0.26
    .SuspendLayout
    -0.26
    æ®ĸ
    -0.26
    è¯ĬæīĢ
    -0.25
    漪
    -0.24
     trickle
    -0.24
    缮çļĦæĺ¯
    -0.24
    ä¸ĢåłĨ
    -0.24
    è¿Ľè¡Įåħ¨éĿ¢
    -0.24
    POSITIVE LOGITS
    dana
    0.30
    çļĦåģļæ³ķ
    0.27
    aze
    0.25
    arkan
    0.25
     Hide
    0.24
    ä¸įåIJĮçļĦ
    0.24
    оÑĦ
    0.24
    xee
    0.24
     emb
    0.24
     exactly
    0.23
    Activations Density 1.074%

    No Known Activations