© 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. 29688
    Prev
    Next
    INDEX
    Explanations

    breaking down complex things

    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
    åĢ¼æĺ¯
    -0.08
    ç¦ģ
    -0.08
    utamente
    -0.07
    ebro
    -0.07
    åĢ¼
    -0.07
    èĢĢ
    -0.07
    áºŃy
    -0.07
     indirectly
    -0.07
    edan
    -0.07
    ä¸ĢéĢļ
    -0.07
    POSITIVE LOGITS
    æ¯ĵ
    0.08
     tackle
    0.08
    ieces
    0.08
     parts
    0.08
    åĪĨ解
    0.08
     manageable
    0.07
     partes
    0.07
    roman
    0.07
    ven
    0.07
     tackles
    0.07
    Activations Density 0.005%

    No Known Activations