© 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. 51263
    Prev
    Next
    INDEX
    Explanations

    located in

    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
     vert
    -0.07
     Marshall
    -0.07
     Vert
    -0.07
    marshall
    -0.07
    _COMMAND
    -0.07
    á»ĭa
    -0.06
    parer
    -0.06
    è¯ģæį®è¯ģæĺİ
    -0.06
    åıªå¾Ĺ
    -0.06
    OFF
    -0.06
    POSITIVE LOGITS
    梦è§ģ
    0.08
    åŀ¢
    0.07
    o
    0.07
    éĻĮ
    0.07
    ...**
    0.07
    dra
    0.07
    hen
    0.07
    ...*
    0.07
    龸çİĭ
    0.07
    æĪij常常
    0.07
    Activations Density 0.140%

    No Known Activations