© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51698
    Prev
    Next
    INDEX
    Explanations

    proof by induction

    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¿¡æģ¯æŁ¥è¯¢
    -0.08
    agia
    -0.07
    æ¸ł
    -0.07
    egna
    -0.07
    èĩªçĶ±æ´»åĬ¨
    -0.07
    hout
    -0.07
    jsonp
    -0.07
    åĩºä¸į
    -0.07
    CharCode
    -0.07
    _bias
    -0.07
    POSITIVE LOGITS
     recursive
    0.08
    éĢĴ
    0.08
     verified
    0.08
     Verified
    0.08
    recursive
    0.08
    Verified
    0.08
     verifier
    0.08
     proof
    0.08
     recurrence
    0.08
    è¯ģæĺİ
    0.08
    Activations Density 0.010%

    No Known Activations