© 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. 20785
    Prev
    Next
    INDEX
    Explanations

    titles, authors, or prices

    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
    ipsis
    -0.08
    </think>
    -0.07
     czar
    -0.07
    èĩªå·±ä¹Ł
    -0.07
     firstname
    -0.07
    ünst
    -0.07
    èĪ¶
    -0.07
    为æŃ¢
    -0.06
     -*
    -0.06
     domic
    -0.06
    POSITIVE LOGITS
    ###
    0.12
    ##
    0.11
     ###
    0.09
     ##
    0.09
    ####
    0.08
     bâ
    0.07
     gelt
    0.07
    áĥ®áĥĿ
    0.06
     ####
    0.06
    estimate
    0.06
    Activations Density 0.239%

    No Known Activations