© 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. 16261
    Prev
    Next
    INDEX
    Explanations

    of + [concept]

    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
    stw
    -0.07
    (s
    -0.07
    stwo
    -0.07
    们çļĦ
    -0.07
    sWith
    -0.06
    QUIRES
    -0.06
    's
    -0.06
    sth
    -0.06
    ’s
    -0.06
    stown
    -0.06
    POSITIVE LOGITS
     kojima
    0.13
     themselves
    0.11
    ä¹Łéĥ½æĺ¯
    0.10
     коÑĤоÑĢÑĭе
    0.10
     коиÑĤо
    0.10
     denen
    0.10
     lesquelles
    0.10
     вÑĢоде
    0.09
     ÙħختÙĦÙģÛĮ
    0.09
     ÙħختÙĦÙģ
    0.09
    Activations Density 0.845%

    No Known Activations