Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 163654
    Prev
    Next
    INDEX
    Explanations

    aque

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ŃåĽ½åζéĢł
    -0.29
     fert
    -0.28
    .construct
    -0.27
    å©ļ
    -0.26
    ç¥Ń
    -0.25
    çķĻä¸ĭ
    -0.25
     Pastor
    -0.24
    æĶ¾å®½
    -0.24
     Bapt
    -0.24
    cej
    -0.24
    POSITIVE LOGITS
     taskId
    0.29
    (shell
    0.27
    aviors
    0.27
    积水
    0.26
    )init
    0.25
     OMAP
    0.25
     accumulate
    0.25
    IDI
    0.25
    积累
    0.25
     degradation
    0.25
    Activations Density 0.001%

    No Known Activations