© 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. 9-TRANSCODER-HP
    7. 29981
    Prev
    Next
    INDEX
    Explanations

    biology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ»
    -0.29
    è°ĥæŁ¥æĺ¾ç¤º
    -0.26
    NotFoundError
    -0.26
    yme
    -0.26
    æĪij说
    -0.26
    ĥģ
    -0.25
    好æĦŁ
    -0.25
    å¾Ī满æĦı
    -0.25
    çķĻä½ı
    -0.24
    è¿Ŀæ³ķçĬ¯ç½ª
    -0.24
    POSITIVE LOGITS
    æķ´
    0.26
     ranks
    0.25
     Rank
    0.25
     Auss
    0.25
    éĢģ
    0.25
    ä¸ī天
    0.25
    سع
    0.25
     eff
    0.24
    .volley
    0.24
    ä¸
    0.24
    Activations Density 10.868%

    No Known Activations