© 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. 61075
    Prev
    Next
    INDEX
    Explanations

    feature norms

    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
     simply
    -0.08
     einfach
    -0.07
    queda
    -0.07
    áng
    -0.07
    éĢļ天
    -0.07
    Supported
    -0.07
     Simply
    -0.07
    çªģ
    -0.07
    .str
    -0.07
    æĺł
    -0.07
    POSITIVE LOGITS
    bane
    0.07
    ecycle
    0.07
    åĽŀåİ»åIJ§
    0.07
     defic
    0.07
    çİ©
    0.07
    asuk
    0.06
    é£
    0.06
    åİ»çİ©
    0.06
    iston
    0.06
    è¿ĺç»Ļ
    0.06
    Activations Density 0.043%

    No Known Activations