© 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. 17603
    Prev
    Next
    INDEX
    Explanations

    article, section, Rule, Chapter

    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
    -cols
    -0.07
    -Smith
    -0.07
    enne
    -0.07
    ascÄĥ
    -0.07
    çĹĩ
    -0.07
    æĸ°å±Ģ
    -0.07
    çĹĩçļĦ
    -0.07
     taraf
    -0.06
    jl
    -0.06
    ->$
    -0.06
    POSITIVE LOGITS
    ï¼ij
    0.09
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.08
     eins
    0.08
    ï¼ĵ
    0.07
    âĢ¦,
    0.07
    IDX
    0.07
    ï¼Ĺ
    0.07
    ï¼ĺ
    0.07
    ï¼ĸ
    0.07
     _______,
    0.07
    Activations Density 0.339%

    No Known Activations