© 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. 2056
    Prev
    Next
    INDEX
    Explanations

    periodontal

    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
    èŀŁ
    -0.08
    èĶ·
    -0.08
    VEST
    -0.07
    éľĵ
    -0.07
    _refl
    -0.07
    秧
    -0.07
    éķ¿ç©º
    -0.07
    abat
    -0.07
    ä¸ĩ件
    -0.07
    æľºç»Ħ
    -0.07
    POSITIVE LOGITS
    çīĻåij¨
    0.09
    ëĭ´
    0.08
    åģ¥åº·çļĦ
    0.08
    fid
    0.08
     пÑĢикоÑĢ
    0.07
    rap
    0.07
    çļĦåģ¥åº·
    0.07
    ä¸ĢåľĪ
    0.07
    auty
    0.07
    大å°Ĩ
    0.07
    Activations Density 0.060%

    No Known Activations