© 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. 60322
    Prev
    Next
    INDEX
    Explanations

    discussion points

    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
    myp
    -0.07
    pada
    -0.07
    ãĥªãĥĥãĤ¯
    -0.07
     bient
    -0.07
    ingo
    -0.07
    hra
    -0.07
    >Type
    -0.06
    ooky
    -0.06
    idio
    -0.06
    .nodeType
    -0.06
    POSITIVE LOGITS
     penc
    0.07
     /*!<
    0.07
    	union
    0.06
    æ¥ł
    0.06
    mentions
    0.06
    æĸĩèģĶ
    0.06
    amol
    0.06
    èĴ¸èĴ¸
    0.06
    Exchange
    0.06
    preneur
    0.06
    Activations Density 0.031%

    No Known Activations