© 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. 7347
    Prev
    Next
    INDEX
    Explanations

    U

    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
    æ°¸ä¹ħ
    -0.44
     permanent
    -0.40
     Permanent
    -0.39
     permanently
    -0.36
    Permanent
    -0.34
    æ°¸
    -0.32
     Forever
    -0.32
    ç»Ī身
    -0.30
     forever
    -0.30
    ä¸įåı¯
    -0.30
    POSITIVE LOGITS
    /respond
    0.28
    åºł
    0.27
    æĬĸ
    0.27
    èĻ»
    0.26
    WISE
    0.26
    课åłĤ
    0.25
    others
    0.25
    åľ¨å¤ĸéĿ¢
    0.25
    ä¼ĹæīĢ
    0.24
    ç½ijç»ľä¼łæĴŃ
    0.24
    Activations Density 0.009%

    No Known Activations