© 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. 3992
    Prev
    Next
    INDEX
    Explanations

    eigenvalue

    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
    .attr
    -0.07
    è§ħ
    -0.07
    å°Ķæĸ¯
    -0.07
    é¢Į
    -0.07
    ẹ
    -0.07
     Contempor
    -0.06
    çĶľåij³
    -0.06
    æľĶ
    -0.06
    ÑĢÑĥбе
    -0.06
    使çĶ¨åĴĮ
    -0.06
    POSITIVE LOGITS
    coder
    0.07
     гÑĢад
    0.07
    azon
    0.07
    ÐľÐļ
    0.07
    abase
    0.07
    eper
    0.07
    uler
    0.07
     coz
    0.07
    illow
    0.07
    ktop
    0.07
    Activations Density 0.002%

    No Known Activations