© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    tool set

    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
    ç±
    -0.07
    ering
    -0.07
    ç§
    -0.07
    .unshift
    -0.07
    åľŃ
    -0.06
     manifest
    -0.06
    eson
    -0.06
    ivalence
    -0.06
    æ·Ģ
    -0.06
    æĿĤ
    -0.06
    POSITIVE LOGITS
    åĪĩå®ŀåģļåĪ°
    0.08
    irik
    0.08
    ael
    0.08
    วย
    0.08
    åĪ¤å¤ĦæľīæľŁå¾ĴåĪij
    0.08
    zl
    0.08
    寬
    0.07
    trup
    0.07
    ZER
    0.07
    vals
    0.07
    Activations Density 0.001%

    No Known Activations