© 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. 48042
    Prev
    Next
    INDEX
    Explanations

    identificationcharacteristicstraits

    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
    importe
    -0.07
    enu
    -0.07
    resh
    -0.07
     issue
    -0.07
    èĬ®
    -0.06
    делÑĮ
    -0.06
     mil
    -0.06
    åIJĴ
    -0.06
     হয়à§ĩ
    -0.06
    æĢİä¹Īèĥ½
    -0.06
    POSITIVE LOGITS
    幸
    0.07
    stripe
    0.07
    _tokenize
    0.07
    æľīæīĢæĢĿ
    0.07
    æĹħ游åĮº
    0.07
    è¿Ľç¤¾åĮº
    0.07
    jectives
    0.07
    åľ¨çĻ½
    0.07
     traits
    0.07
    brero
    0.07
    Activations Density 0.030%

    No Known Activations