© 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. 27213
    Prev
    Next
    INDEX
    Explanations

    numbers followed by `?`

    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
    rah
    -0.07
     Conservative
    -0.06
    ÙĪØ®
    -0.06
    æĶ¹è§Ĥ
    -0.06
    èĢĮå¼Ĥ
    -0.06
    举åIJ´
    -0.06
    庶
    -0.06
    ikov
    -0.06
    _GENERIC
    -0.06
    åĮºçº§
    -0.06
    POSITIVE LOGITS
    æĪij们æĿ¥
    0.08
    -repeat
    0.08
    Mathf
    0.08
     daarmee
    0.08
    ç§ķ
    0.08
    }elseif
    0.07
    ä¸ĭåIJĮ
    0.07
    менÑĥ
    0.07
    åĨįæİ¥
    0.07
    ä¸ĭéĿ¢å°±
    0.07
    Activations Density 0.071%

    No Known Activations