© 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. 25267
    Prev
    Next
    INDEX
    Explanations

    sum counts for my data

    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
     Peker
    -0.08
    /../
    -0.08
     serialVersionUID
    -0.08
    æĪijæĿ¥è¯´
    -0.08
    .toFixed
    -0.08
    Configurer
    -0.08
    szt
    -0.08
     @}
    -0.08
    деÑĤÑģÑı
    -0.07
     Bagno
    -0.07
    POSITIVE LOGITS
    ı
    0.07
    æ·±
    0.07
    群
    0.06
    å
    0.06
    áĬIJ
    0.06
    çIJ
    0.06
     Rosario
    0.06
    éĻį
    0.06
    åĩĨ
    0.06
    éĽ¯
    0.06
    Activations Density 0.003%

    No Known Activations