© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25126
    Prev
    Next
    INDEX
    Explanations

    circuit, Hot, Donald, want

    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
    管çIJĨç±»
    -0.08
    管çIJĨä¸İ
    -0.07
    opup
    -0.07
    æĤį
    -0.07
    -modal
    -0.07
    ilik
    -0.07
    ç½
    -0.06
    aux
    -0.06
     Bran
    -0.06
    GM
    -0.06
    POSITIVE LOGITS
    è¶ģ
    0.08
    éĺ¿å§Ĩæĸ¯
    0.08
    onsor
    0.08
    ylum
    0.08
    bugs
    0.08
    sii
    0.08
     lus
    0.08
    chetta
    0.08
    ACLE
    0.08
    ULATOR
    0.08
    Activations Density 0.030%

    No Known Activations