© 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. 19383
    Prev
    Next
    INDEX
    Explanations

    /res or /values

    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
    pa
    -0.07
    byn
    -0.07
    _accum
    -0.07
    éĻįèIJ½
    -0.07
    iser
    -0.07
    `\
    -0.07
    //--
    -0.07
     skut
    -0.07
    versions
    -0.07
    OSH
    -0.07
    POSITIVE LOGITS
    çŁ³éŨ
    0.08
    ourke
    0.07
    unte
    0.07
     Kuh
    0.07
    æĨ¬
    0.07
    еÑĢна
    0.07
    à¸ī
    0.06
    aday
    0.06
    ayani
    0.06
    quem
    0.06
    Activations Density 0.195%

    No Known Activations