© 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. 1023
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    çķĮ
    -0.07
    æľ¬æ¥¼
    -0.07
    çŃīå¾ħ
    -0.06
    åı¯ä»¥è¯´
    -0.06
    佩æĪ´åı£ç½©
    -0.06
     Vista
    -0.06
    alba
    -0.06
     Mud
    -0.06
    纹
    -0.06
    بات
    -0.06
    POSITIVE LOGITS
    çļĦç¼ĺæķħ
    0.10
    ãģĭãĤīãģŃ
    0.09
     appunto
    0.08
    uent
    0.08
    .createFrom
    0.08
    à¹Ħà¸ĩ
    0.08
    æĭ¯
    0.08
    succ
    0.07
    è´£ç¼ĸ
    0.07
    åĽ±
    0.07
    Activations Density 0.092%

    No Known Activations