© 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. 9552
    Prev
    Next
    INDEX
    Explanations

    release of dye

    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
    æ¢Ĩ
    -0.08
    çĶµä»·
    -0.08
    çĭ¬åįł
    -0.07
    à®Łà¯ģதà¯įதà¯ģ
    -0.07
    _imm
    -0.07
    ä¹ħè¿ľ
    -0.07
    大åı¯
    -0.07
    żeÅĦ
    -0.07
    zin
    -0.07
    oming
    -0.06
    POSITIVE LOGITS
     Democr
    0.08
     deposits
    0.08
    åį´å§ĭç»Ī
    0.07
    argent
    0.07
    驻马
    0.07
    èĩªå·±è¢«
    0.07
     дÑĢÑĥ
    0.06
    arrer
    0.06
    handled
    0.06
     fund
    0.06
    Activations Density 0.002%

    No Known Activations