© 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. 56254
    Prev
    Next
    INDEX
    Explanations

    division or multiple checks

    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
    ered
    -0.07
    ionic
    -0.07
     itself
    -0.07
     Simpl
    -0.06
    ering
    -0.06
     cort
    -0.06
    var
    -0.06
    éĻį
    -0.06
    ir
    -0.06
    vole
    -0.06
    POSITIVE LOGITS
    exels
    0.08
    æļĤè¡Į
    0.08
    _BU
    0.08
    жан
    0.08
    viso
    0.08
    tus
    0.08
    ollah
    0.07
    anni
    0.07
    arrants
    0.07
     contrac
    0.07
    Activations Density 0.018%

    No Known Activations