© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2412
    Prev
    Next
    INDEX
    Explanations

    preceding closing parenthesis/punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĭåIJĮ
    -0.08
    幸
    -0.07
    æĭŁ
    -0.07
    ׳×Ļ×ķת
    -0.07
    atz
    -0.06
    æľĭ
    -0.06
    è¦ı
    -0.06
    åĵªå¤©
    -0.06
    ÏĨη
    -0.06
    åĪ¨
    -0.06
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.08
    nam
    0.08
    ingg
    0.07
    ASN
    0.07
    èģĶç³»æĪij们
    0.07
     Couldn
    0.07
    ipt
    0.07
    iby
    0.07
    [`
    0.07
    _lifetime
    0.06
    Activations Density 0.236%

    No Known Activations