© 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. 22363
    Prev
    Next
    INDEX
    Explanations

    positive curvature

    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
    _except
    -0.08
    ç³»
    -0.07
    é¦Ļ
    -0.07
    .har
    -0.07
     seri
    -0.07
    VD
    -0.07
    ,default
    -0.07
     Stol
    -0.07
    é¦ĭ
    -0.07
    åŃļ
    -0.06
    POSITIVE LOGITS
    amakan
    0.08
    æľīåħ³æ³ķå¾ĭæ³ķè§Ħ
    0.07
    orent
    0.07
    asma
    0.07
    çķĮçļĦ
    0.07
    à¤ļà¥įà¤Ľ
    0.07
    åħĥèĢģ
    0.07
    elt
    0.07
    ever
    0.07
    ume
    0.07
    Activations Density 0.028%

    No Known Activations