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. 162258
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     mouths
    -0.26
    è¿ĽæŃ¥
    -0.26
    ä¸ĢæŃ¥
    -0.26
    éĢģæĿ¥
    -0.25
     translating
    -0.25
    jets
    -0.25
     banged
    -0.25
     advances
    -0.24
    æľ«
    -0.24
     конÑĤ
    -0.24
    POSITIVE LOGITS
    积
    0.33
     nÄĥng
    0.29
    ç©į
    0.28
    æķ´
    0.27
     isinstance
    0.26
     pháºŃn
    0.25
    积累
    0.24
     Iz
    0.24
    æħİéĩį
    0.24
    漫
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.