© 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. 50249
    Prev
    Next
    INDEX
    Explanations

    type declarations following keywords

    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
    .Util
    -0.07
    koa
    -0.06
    itm
    -0.06
    inkel
    -0.06
    æľĽ
    -0.06
    apon
    -0.06
     sprintf
    -0.06
     Salvatore
    -0.06
    ?key
    -0.06
    ea
    -0.06
    POSITIVE LOGITS
    æįį
    0.08
    ủng
    0.08
    WXYZ
    0.08
     McB
    0.07
    æ°´åİ¿
    0.07
    游åĪĥ
    0.07
    åıĬéħį件
    0.07
    assion
    0.07
    éĻª
    0.07
    _arguments
    0.07
    Activations Density 0.014%

    No Known Activations