© 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. 62247
    Prev
    Next
    INDEX
    Explanations

    special characters and numbers

    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
    æĪIJ家
    -0.06
     labor
    -0.06
    ITHER
    -0.06
    ụng
    -0.06
    ef
    -0.06
    cher
    -0.06
    PELL
    -0.06
    Unless
    -0.06
    IMER
    -0.06
    òa
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įè¡Į
    0.08
    urie
    0.08
    éĹ®é¢ĺæŶ
    0.08
    æĬĺä¸į
    0.08
    ãģ¨ãģªãĤĭãģ¨
    0.07
    éĤ£å°±
    0.07
    æĪĸ以ä¸Ĭ
    0.07
     frau
    0.07
    ulp
    0.07
    ruc
    0.07
    Activations Density 0.010%

    No Known Activations