© 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. 13014
    Prev
    Next
    INDEX
    Explanations

    semi-automatic

    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
    abwe
    -0.07
     Stutt
    -0.07
    olan
    -0.07
    åľºä¸Ĭ
    -0.07
    igner
    -0.07
    ffel
    -0.07
    łĢ
    -0.07
    jem
    -0.06
     ÑģбÑĢо
    -0.06
     Libri
    -0.06
    POSITIVE LOGITS
    å°±æĺ¯æĮĩ
    0.08
    顾åIJįæĢĿä¹ī
    0.07
    èĻ±
    0.07
    ¾
    0.07
    meric
    0.07
    enarios
    0.06
    æĺ¯æĮĩ
    0.06
    æĸ°æ¦Ĥ念
    0.06
    izzle
    0.06
    idth
    0.06
    Activations Density 0.128%

    No Known Activations