© 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. 62625
    Prev
    Next
    INDEX
    Explanations

    new value

    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
    สำà¹Ģรà¹ĩà¸Ī
    -0.08
     Packet
    -0.07
    æĽ²æ±Ł
    -0.07
     guaranteed
    -0.07
    italia
    -0.07
    ç¬Ļ
    -0.07
    ç»ĩ女
    -0.06
    å¿ĥ缮
    -0.06
    egen
    -0.06
    eof
    -0.06
    POSITIVE LOGITS
    èĬľ
    0.08
    éĩįæķ´
    0.08
    /android
    0.07
    ConverterFactory
    0.07
     ignored
    0.07
    ç§ijåѦ
    0.07
    ri
    0.07
    chau
    0.07
    çļĦèĩªçĦ¶
    0.07
     Ignore
    0.07
    Activations Density 0.028%

    No Known Activations