© 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. 18595
    Prev
    Next
    INDEX
    Explanations

    quantities or comparisons

    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
    临
    -0.07
    termin
    -0.07
     Rang
    -0.07
    模èĮĥ
    -0.06
    èĩ¨
    -0.06
    strand
    -0.06
    ç»ĺ
    -0.06
    endah
    -0.06
    ä¸ĢæĻĤ
    -0.06
    uled
    -0.06
    POSITIVE LOGITS
     Overall
    0.10
    combined
    0.10
    åIJĮæĹ¶å¯¹
    0.09
    comb
    0.09
    主è¦ģéĴĪ对
    0.09
     Separate
    0.09
     overall
    0.09
    overall
    0.09
    Overall
    0.09
    çļĦæķ´ä½ĵ
    0.09
    Activations Density 0.387%

    No Known Activations