© 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. 63341
    Prev
    Next
    INDEX
    Explanations

    code punctuation or {return

    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
    lesc
    -0.07
    ELLO
    -0.07
    æŃ¦ä¾¯
    -0.07
    ostas
    -0.07
    æĢ§è³ª
    -0.06
    )))),
    -0.06
    ulp
    -0.06
    iamo
    -0.06
    åIJij
    -0.06
    azzo
    -0.06
    POSITIVE LOGITS
     verf
    0.08
    èĪŀåı°ä¸Ĭ
    0.07
    è¿ĶåĽŀåĪĹ表
    0.07
    åľ°å¤´
    0.07
    {return
    0.07
    çĶ£
    0.07
    IFS
    0.07
    veld
    0.06
    渴æ±Ĥ
    0.06
    ueur
    0.06
    Activations Density 0.035%

    No Known Activations