© 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. 32312
    Prev
    Next
    INDEX
    Explanations

    treat as

    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
    ooks
    -0.08
    æĪ¿å¤©ä¸ĭ
    -0.08
    尼奥
    -0.07
    åĩºäºĨä¸Ģ个
    -0.07
    ushman
    -0.07
    upd
    -0.07
    à¸ŀร
    -0.07
     оÑĤÑĤ
    -0.07
    gomery
    -0.07
    ERM
    -0.07
    POSITIVE LOGITS
    ëĿ¼ëıĦ
    0.07
    éĹ®é¢ĺè¿Ľè¡Į
    0.07
    åºĦ
    0.07
     serious
    0.07
    fragen
    0.06
    并积æŀģ
    0.06
    æĶ¿æ²»ä»»åĬ¡
    0.06
    çĻ¾åĪĨçĻ¾
    0.06
    妥妥
    0.06
    并ç»ĵåIJĪ
    0.06
    Activations Density 0.016%

    No Known Activations