© 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. 60638
    Prev
    Next
    INDEX
    Explanations

    code structure and symbols

    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
    DIR
    -0.08
    /Graphics
    -0.08
    entif
    -0.07
    èĹ©
    -0.07
    é»ĦæŁIJ
    -0.07
    ooth
    -0.07
    ãģ¨è¨ĢãģĪãģ°
    -0.07
    .Generation
    -0.07
    .gnu
    -0.07
    /Gate
    -0.07
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.07
    ç®Ģ称
    0.07
    forcer
    0.07
    çĽ¸å¯¹åºĶçļĦ
    0.06
    顾åIJįæĢĿä¹ī
    0.06
    imus
    0.06
    KeyName
    0.06
    uesa
    0.06
    andone
    0.06
     obr
    0.06
    Activations Density 0.325%

    No Known Activations