© 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. 8910
    Prev
    Next
    INDEX
    Explanations

    calculate profit, potential, or formulas

    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
     NotÃŃcias
    -0.07
    åĴĮéĿŀ
    -0.07
    ietta
    -0.07
    幻影
    -0.07
    è·¯éĢı
    -0.07
     tails
    -0.07
    计åħ¥
    -0.06
    à¬Ľ
    -0.06
    marker
    -0.06
    æľįåĬ¡ä¸Ńå¿ĥ
    -0.06
    POSITIVE LOGITS
    ä¹ĭéĹ´çļĦåħ³ç³»
    0.08
     quantity
    0.08
     Quantity
    0.08
    çļĦåħ³ç³»
    0.08
    Quantity
    0.08
    quantity
    0.08
    ToObject
    0.08
    å¦Ĥæŀľä¸Ģ个
    0.07
    [v
    0.07
    åĽłæŀľåħ³ç³»
    0.07
    Activations Density 0.008%

    No Known Activations