© 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. 49806
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by their suffixes

    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
    quires
    -0.08
     ];
    -0.07
    culate
    -0.07
    ï¼Ī
    -0.06
     };
    -0.06
    аз
    -0.06
    }'.
    -0.06
    (
    -0.06
    ÙĬØ·
    -0.06
    itting
    -0.06
    POSITIVE LOGITS
    èĩªå·±
    0.08
    adays
    0.08
    onacci
    0.08
    etheless
    0.08
    odore
    0.08
    ĵĺ
    0.08
    æĺ¯ä¸Ģç§įéĿŀ常
    0.07
    áĬ¥
    0.07
    èĩªå·±è¢«
    0.07
    èĩªå·±æ²¡æľī
    0.07
    Activations Density 0.257%

    No Known Activations