© 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. 31834
    Prev
    Next
    INDEX
    Explanations

    electrolyte

    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
    OrUpdate
    -0.09
    mehr
    -0.08
    äºİä¸ĸ
    -0.08
    ely
    -0.07
    /or
    -0.07
    ese
    -0.07
    yar
    -0.07
    mah
    -0.07
    quam
    -0.07
    åŃIJéĩĮ
    -0.07
    POSITIVE LOGITS
    è´¨çļĦ
    0.09
    anguage
    0.08
    ic
    0.08
    reich
    0.08
    ernen
    0.08
    phone
    0.08
    ipse
    0.07
    ед
    0.07
    ptic
    0.07
    Ñģ
    0.07
    Activations Density 0.010%

    No Known Activations