© 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. 58678
    Prev
    Next
    INDEX
    Explanations

    selection and rules

    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
    è¿Ļç§įåģļæ³ķ
    -0.08
    ĸ
    -0.08
     Reinh
    -0.08
    è¿Ļç§įè¡Į为
    -0.07
    ër
    -0.07
    çĿ¡ä¸įçĿĢ
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    cini
    -0.07
    äºijå³°
    -0.07
    解åĨ³éĹ®é¢ĺçļĦ
    -0.07
    POSITIVE LOGITS
     rules
    0.08
    è§ĦåĪĻ
    0.08
    çļĦè§ĦåĪĻ
    0.08
    yarat
    0.08
    bidden
    0.08
    éĻIJ
    0.07
     rule
    0.07
    -rule
    0.07
    åIJķ
    0.07
     Rules
    0.07
    Activations Density 0.002%

    No Known Activations