© 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. 41215
    Prev
    Next
    INDEX
    Explanations

    column names and assignments

    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
    ä¸ĢäºĮ
    -0.07
    ify
    -0.07
    ical
    -0.06
    æ¶Į
    -0.06
    heim
    -0.06
    assel
    -0.06
    ä¸ĩåĽ½
    -0.06
    ilyn
    -0.06
    ä¸ĢåŃĹ
    -0.06
     Ø·ÙĦ
    -0.06
    POSITIVE LOGITS
    æ±ģ
    0.08
    Assignable
    0.08
    _PWM
    0.07
     PÃļBL
    0.07
    _userdata
    0.07
    [__
    0.07
    ÅĤod
    0.07
    åħĭåħ°
    0.07
    uken
    0.07
    upp
    0.07
    Activations Density 0.002%

    No Known Activations