© 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. 24815
    Prev
    Next
    INDEX
    Explanations

    agency names

    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
    imonial
    -0.08
    >:</
    -0.08
    ä¾Ŀ
    -0.07
    ungeons
    -0.07
    _MPI
    -0.07
    _rq
    -0.07
    rau
    -0.07
    åŃĺåľ¨ä¸ĢäºĽ
    -0.07
    ulich
    -0.06
    .':
    -0.06
    POSITIVE LOGITS
    åīįèĮħ
    0.07
     etc
    0.07
     seminal
    0.07
    è°Ī
    0.07
    æĽ´å¤ļåħ³äºİ
    0.06
     Boom
    0.06
    éh
    0.06
    _wh
    0.06
    çŃīè¿Ľè¡Į
    0.06
    ä¸Ńå¿ĥçŃī
    0.06
    Activations Density 0.021%

    No Known Activations