© 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. 1461
    Prev
    Next
    INDEX
    Explanations

    footnotes and references

    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
    gaste
    -0.08
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.07
     ——
    -0.07
     Mondi
    -0.06
    èŁ
    -0.06
    вок
    -0.06
     nullptr
    -0.06
    è·¯éĢı社
    -0.06
    ä¹ĥ
    -0.06
    æľĽ
    -0.06
    POSITIVE LOGITS
    æĺ¥æĿ¥
    0.07
    è§ģåĪ°äºĨ
    0.07
    è§ģæĪij
    0.07
    osit
    0.07
    éz
    0.07
    http
    0.07
    itier
    0.07
     Reit
    0.07
    uin
    0.06
    è§ģéĿ¢
    0.06
    Activations Density 0.085%

    No Known Activations