© 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. 20246
    Prev
    Next
    INDEX
    Explanations

    not or excluded

    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
    anka
    -0.08
    ern
    -0.08
    æĤ¨çİ°åľ¨çļĦä½įç½®
    -0.07
    çİ°åľ¨å¼Ģå§ĭ
    -0.07
    éľĢè¦ģåIJĮ
    -0.07
    rete
    -0.07
    /plain
    -0.07
    dez
    -0.07
    çĻ¾å¼º
    -0.07
    headed
    -0.07
    POSITIVE LOGITS
    æĢ»
    0.10
    æĢ»æĶ¯
    0.09
     total
    0.08
    total
    0.07
    estan
    0.07
    -total
    0.07
     Total
    0.07
     sum
    0.07
    éĢļ
    0.07
    arien
    0.07
    Activations Density 0.008%

    No Known Activations