© 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. 49419
    Prev
    Next
    INDEX
    Explanations

    must be

    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
    åħĪåĪ°
    -0.07
    解åĨ³éĹ®é¢ĺ
    -0.07
    æľŃ
    -0.07
    æĽ´å¤ļåĨħ容
    -0.07
    fang
    -0.07
    æĽ´å¤ļ精彩åĨħ容
    -0.07
    åıĪå¤ļ
    -0.07
    ä¹ŁæľīæīĢ
    -0.07
    ä¹Łä¸Ģ缴
    -0.07
    pli
    -0.07
    POSITIVE LOGITS
    ä¸įä»ħèĥ½å¤Ł
    0.08
    æĸ°åĬłåĿ¡
    0.07
    jenigen
    0.07
    ä½ĻåĬĽ
    0.07
     **-
    0.07
    insk
    0.07
    —who
    0.07
    ä¸įä»ħåı¯ä»¥
    0.06
    วล
    0.06
    <strong
    0.06
    Activations Density 0.023%

    No Known Activations