© 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. 3716
    Prev
    Next
    INDEX
    Explanations

    parentheses and mathematical expressions

    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
    åĩºèį·
    -0.07
    èļģ
    -0.07
    ix
    -0.06
    æ·ij
    -0.06
    ваÑİ
    -0.06
    isht
    -0.06
    _OLD
    -0.06
    tig
    -0.06
    æłĦ
    -0.06
    ][:
    -0.06
    POSITIVE LOGITS
    ezo
    0.08
    å§ĭç¥ĸ
    0.07
    èĨł
    0.07
    holz
    0.07
    ¾¸
    0.07
    ä¸įä½ıäºĨ
    0.07
    kits
    0.07
    äºĨäºĽ
    0.07
    ensburg
    0.07
    _lane
    0.07
    Activations Density 0.007%

    No Known Activations