© 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. 38519
    Prev
    Next
    INDEX
    Explanations

    derivative, order, selector

    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
    áºŃm
    -0.07
    Ci
    -0.07
     unbe
    -0.06
    ciano
    -0.06
    зал
    -0.06
    Cx
    -0.06
    CI
    -0.06
    aves
    -0.06
    c
    -0.06
     Caucus
    -0.06
    POSITIVE LOGITS
    ç§ĭ鼨
    0.09
    avais
    0.07
    OOT
    0.07
    .deepcopy
    0.07
    è¸ıè¸ıå®ŀå®ŀ
    0.07
    occa
    0.07
    èķĥ
    0.07
    åĽłä¸ºè¿ĻäºĽ
    0.07
    è¿Ļ两款
    0.07
    Ỽ
    0.07
    Activations Density 0.011%

    No Known Activations