© 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. 28402
    Prev
    Next
    INDEX
    Explanations

    rotation and hybridization

    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
    ianti
    -0.07
    plement
    -0.07
    å±ij
    -0.07
    è¸ıæŃ¥
    -0.07
    æ·¡æ·¡
    -0.06
     level
    -0.06
    æĮĩ纹
    -0.06
    ç±į
    -0.06
    enger
    -0.06
    ваÑĢ
    -0.06
    POSITIVE LOGITS
     Willis
    0.07
    ÙıÙħÙĴ
    0.07
    ZO
    0.07
     dota
    0.07
    lds
    0.07
    uva
    0.07
     Cone
    0.07
    çļĦ主è§Ĥ
    0.07
     reco
    0.07
    ornings
    0.07
    Activations Density 0.004%

    No Known Activations