© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7102
    Prev
    Next
    INDEX
    Explanations

    Word definitions and meanings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¼ĸ
    -0.28
     primitive
    -0.27
    æĹ©æĻļ
    -0.27
     bez
    -0.27
     Primitive
    -0.27
    ÑĮ
    -0.26
    åİŁå§ĭ
    -0.26
    ä¹Łæĺ¯ä¸Ģ个
    -0.26
    骨
    -0.25
    ä¸įå¦Ĥ
    -0.25
    POSITIVE LOGITS
    oload
    0.27
    èĻij
    0.27
    avigation
    0.27
    éĴ¿
    0.26
    oose
    0.26
    orno
    0.26
    otime
    0.26
    bia
    0.26
    éĵ¨
    0.25
    gravity
    0.25
    Activations Density 0.002%

    No Known Activations