© 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. 41587
    Prev
    Next
    INDEX
    Explanations

    despite, though, when

    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
    èĻ½çĦ¶æ²¡æľī
    -0.10
     WITHOUT
    -0.10
    WITHOUT
    -0.09
    èĻ½çĦ¶æĪij们
    -0.08
     smÄĽ
    -0.08
    agli
    -0.08
    åij½è¿IJåħ±åIJĮä½ĵ
    -0.08
    without
    -0.08
    arco
    -0.08
    ByExample
    -0.08
    POSITIVE LOGITS
     otherwise
    0.10
     pourtant
    0.09
     ostensibly
    0.09
     supposedly
    0.09
     seemingly
    0.08
    æĺİæĺİ
    0.08
    çľĭä¼¼
    0.08
    çľĭèµ·æĿ¥å¾Ī
    0.07
     supposed
    0.07
    ??
    0.07
    Activations Density 0.248%

    No Known Activations