© 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. 56580
    Prev
    Next
    INDEX
    Explanations

    Made, say, how, addressed

    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
     X
    -0.06
     R
    -0.06
    inning
    -0.06
    æ¬
    -0.05
    å¸Ŀ
    -0.05
    æ´ĭ
    -0.05
    è¹
    -0.05
    å½Ŀ
    -0.05
    stell
    -0.05
     :
    -0.05
    POSITIVE LOGITS
    ãĥªãĤ¨
    0.08
     Pue
    0.08
    eschi
    0.08
    æľĢç»ĪçļĦ
    0.08
    æľĢåIJİåľ¨
    0.08
    è¿ĻäºĽéĥ½æĺ¯
    0.08
    ilup
    0.08
    hoff
    0.08
    FAQ
    0.08
    lak
    0.08
    Activations Density 0.023%

    No Known Activations