© 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. 33198
    Prev
    Next
    INDEX
    Explanations

    numbers and analysis

    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
    æľĢåŁºæľ¬
    -0.08
    å³
    -0.07
    irl
    -0.07
    æµģæ°´
    -0.07
    ould
    -0.06
    äºĭåīį
    -0.06
    æĥ³èµ·
    -0.06
    æľªå¿ħ
    -0.06
    jun
    -0.06
    æľīæĦŁ
    -0.06
    POSITIVE LOGITS
    å¹´çļĦåıijå±ķ
    0.08
    LEC
    0.08
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ģาร
    0.08
    åĪĽå»ºäºĨ
    0.08
    ulings
    0.08
     ÑģоздаеÑĤ
    0.08
    ijek
    0.07
    åıĪæĺ¯ä¸Ģ个
    0.07
    æµĴ
    0.07
    [,]
    0.07
    Activations Density 0.006%

    No Known Activations