© 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. 61105
    Prev
    Next
    INDEX
    Explanations

    pairings

    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
    亢
    -0.07
    ä¸ĢåĨį
    -0.07
    inker
    -0.07
    享
    -0.06
    ä¸īç±»
    -0.06
    oky
    -0.06
    jut
    -0.06
    èijĨ
    -0.06
    æĪijåĴĮæĪijçļĦ
    -0.06
     Mot
    -0.06
    POSITIVE LOGITS
    .prot
    0.08
    å®īè¾¾
    0.07
    èħ¹é»ij
    0.07
    解éĩĪ
    0.07
    注åĨĮåı·
    0.07
    engew
    0.07
    angelo
    0.07
    ç»ĵ
    0.07
    åIJĮ人
    0.07
     Bois
    0.07
    Activations Density 0.097%

    No Known Activations