© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14094
    Prev
    Next
    INDEX
    Explanations

    ðŁĵĵO

    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
    inat
    -0.06
    æħĪ祥
    -0.06
    ime
    -0.06
    imal
    -0.06
    ston
    -0.06
    inges
    -0.06
    deaux
    -0.06
    eware
    -0.06
    è£ı
    -0.05
    baus
    -0.05
    POSITIVE LOGITS
    ï¸ı
    0.10
    ï¸İ
    0.09
    æľĢæĸ°æ¶Īæģ¯
    0.07
    ר×Ķ
    0.07
    çī¹å°Ķ
    0.07
    å½ĵå¿ĥ
    0.07
    家ä¼Ļ
    0.07
    ÑĢо
    0.07
    ⾨
    0.07
    van
    0.07
    Activations Density 0.010%

    No Known Activations