© 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. 10137
    Prev
    Next
    INDEX
    Explanations

    impact on

    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
    bies
    -0.08
    zinha
    -0.08
    ightly
    -0.08
    /or
    -0.08
    hood
    -0.07
    semble
    -0.07
    afa
    -0.07
    æĥħçļĦ
    -0.07
    ekt
    -0.07
    prinz
    -0.07
    POSITIVE LOGITS
    аÑĤÑĮ
    0.10
    alani
    0.08
    edicine
    0.08
    ywa
    0.08
    ยà¸Ļà¸ķรà¹Į
    0.08
    aglia
    0.08
    SSIP
    0.08
    itié
    0.08
    ool
    0.08
    tual
    0.07
    Activations Density 0.028%

    No Known Activations