© 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. 19-TRANSCODER-HP
    7. 9123
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous scraped text

    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
    çļĦæĪĺçķ¥
    -0.29
    ment
    -0.26
    ä¸ĩ个
    -0.26
    æĹłä¸į
    -0.26
    member
    -0.25
    çļĦæķ´ä½ĵ
    -0.25
    ........................
    -0.25
    ç³»
    -0.24
    æĪĺçķ¥æĢ§
    -0.23
    æĻĥ
    -0.23
    POSITIVE LOGITS
    æ¢ĵ
    0.27
    Permanent
    0.27
     Permanent
    0.26
    -Star
    0.26
     defaults
    0.26
    æĭĸæ¬ł
    0.25
    erez
    0.25
    æ¡ĥåľĴ
    0.24
    RON
    0.24
    <cv
    0.24
    Activations Density 0.005%

    No Known Activations