© 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. 38971
    Prev
    Next
    INDEX
    Explanations

    what is, round, true/false

    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
    çĥ¦
    -0.07
    rop
    -0.06
    ron
    -0.06
    ON
    -0.06
    alm
    -0.06
    ura
    -0.06
    berg
    -0.06
    丫头
    -0.06
    éĤ£åı¯
    -0.06
    AND
    -0.06
    POSITIVE LOGITS
    иÑĤоÑĢ
    0.10
    æĺ¥æļĸ
    0.09
     {*
    0.09
    ebr
    0.08
    hci
    0.08
    æİĴåIJį第
    0.08
    çĥŃéŨæłĩçŃ¾
    0.08
    ابة
    0.07
    -du
    0.07
    ÑĢаÑĤоÑĢ
    0.07
    Activations Density 0.023%

    No Known Activations