© 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. 19654
    Prev
    Next
    INDEX
    Explanations

    mirrored surfaces and angles

    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
    pm
    -0.08
    è¶Ł
    -0.07
    åĢĴ
    -0.06
    ä½ľæģ¯æŶéĹ´
    -0.06
    å¯Ĩ
    -0.06
    å¯Ĩä¸įåı¯
    -0.06
    åı¯ä½¿çĶ¨
    -0.06
    å¯ĩ
    -0.06
     prek
    -0.06
    å½¼æѤçļĦ
    -0.06
    POSITIVE LOGITS
    æ°¸è¿ľ
    0.09
    Ñģегда
    0.08
     selalu
    0.08
    æ°¸è¿ľæĺ¯
    0.07
     dilat
    0.07
    always
    0.07
    æ°¸éģł
    0.07
    inke
    0.07
    angent
    0.07
    (sizeof
    0.07
    Activations Density 0.003%

    No Known Activations