© 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. 3657
    Prev
    Next
    INDEX
    Explanations

    models, math, length, theta, speech, offenders, crossdresser

    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°±
    -0.08
    顺æīĭ
    -0.08
    bast
    -0.08
    åħĭ森
    -0.08
    æŃ¤èµ·
    -0.08
    åģıå¼±
    -0.07
    æŀĦæĪIJçĬ¯ç½ªçļĦ
    -0.07
     biases
    -0.07
    urga
    -0.07
    schw
    -0.07
    POSITIVE LOGITS
    åŃĺ
    0.08
    åľ¨è¿Ļ段æŶéĹ´
    0.08
    æķ°åѦ
    0.08
    建模
    0.08
    à¸ŀล
    0.07
     modeled
    0.07
    æ¯ıå°ıæŶ
    0.07
     mathematics
    0.07
     algebra
    0.07
    éļıçĿĢæŶéĹ´çļĦ
    0.07
    Activations Density 0.021%

    No Known Activations