© 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. 22621
    Prev
    Next
    INDEX
    Explanations

    expression syntax

    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
    aroo
    -0.09
    åıĸçļĦ
    -0.08
    erah
    -0.07
    evere
    -0.07
    çĻ¾äºĭ
    -0.07
    RequestMethod
    -0.07
    æ·
    -0.07
    eut
    -0.07
    ÑĢевно
    -0.06
    /csv
    -0.06
    POSITIVE LOGITS
     synt
    0.09
     ::=
    0.09
     expressions
    0.09
    表达å¼ı
    0.09
     expression
    0.08
     clauses
    0.08
     paren
    0.08
     infix
    0.08
    idget
    0.08
    æŀĦéĢł
    0.08
    Activations Density 0.031%

    No Known Activations