© 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. 57723
    Prev
    Next
    INDEX
    Explanations

    seeing different cases

    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
    éĶĢåĶ®åıĬ
    -0.07
    ĥģ
    -0.06
    agra
    -0.06
    ilas
    -0.06
    æŶæīĢ
    -0.06
    计ç®Ĺæľºè½¯ç¡¬ä»¶
    -0.06
    zea
    -0.06
    ξι
    -0.06
     evidently
    -0.06
    åĴĮéĹ®é¢ĺ
    -0.06
    POSITIVE LOGITS
    æı
    0.08
    æľĪçĶŁ
    0.08
    éģĵè¿ľ
    0.08
    erci
    0.08
    éments
    0.07
    essen
    0.07
    ÑĨÑĮ
    0.07
    ĵĺ
    0.07
    ä¸įæĿ¥
    0.07
    á»Ĺ
    0.07
    Activations Density 0.017%

    No Known Activations