© 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. 22512
    Prev
    Next
    INDEX
    Explanations

    flashing light

    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
    è´¢
    -0.07
    害
    -0.07
    ç¼Ŀ
    -0.06
    æŃ¤é¡¹
    -0.06
    uter
    -0.06
    ming
    -0.06
     акÑĤ
    -0.06
    пÑĥбли
    -0.06
    _logs
    -0.06
    å¤ļäºĨ
    -0.06
    POSITIVE LOGITS
    ãģ©ãĤĮãĤĤ
    0.08
    ritel
    0.08
    etc
    0.08
    ÙĬاس
    0.07
    rape
    0.07
    chnet
    0.07
    agy
    0.07
    alion
    0.07
    ares
    0.07
    pread
    0.07
    Activations Density 0.002%

    No Known Activations