© 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. 3440
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    uld
    -0.08
    ç¾İåī§
    -0.07
    oby
    -0.07
     beleg
    -0.07
    auc
    -0.07
    ogen
    -0.07
    éo
    -0.07
    har
    -0.06
    ×
    -0.06
    —who
    -0.06
    POSITIVE LOGITS
    utton
    0.07
    èĩªå·±çļĦ身ä½ĵ
    0.06
     imprint
    0.06
     suss
    0.06
    subpackage
    0.06
     Impress
    0.06
    andid
    0.06
    PERT
    0.06
    terrain
    0.06
    মন
    0.06
    Activations Density 0.067%

    No Known Activations