© 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. 19133
    Prev
    Next
    INDEX
    Explanations

    time stamps

    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
    ushi
    -0.06
    åºIJ
    -0.06
    ehr
    -0.06
    éĢļ
    -0.06
    æĺĨ
    -0.06
    ()
    -0.06
    adoo
    -0.05
    é£İåĬĽ
    -0.05
    éĽªå³°
    -0.05
    ارÙĤØ©
    -0.05
    POSITIVE LOGITS
    ìĶĢ
    0.09
    ä»»ä½ķä¿Ŀè¯ģ
    0.09
    uncios
    0.08
    izat
    0.08
    ikum
    0.08
    èĨĽ
    0.08
     immense
    0.08
    æľ¬æ³ķ
    0.08
    两ä¸ĩ
    0.08
    ername
    0.08
    Activations Density 0.022%

    No Known Activations