© 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. 34546
    Prev
    Next
    INDEX
    Explanations

    thanks and help

    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
    åħ¶å®ŀæĺ¯
    -0.07
    appa
    -0.07
    arta
    -0.06
    ...',
    -0.06
    oline
    -0.06
    $',
    -0.06
    ette
    -0.06
    ollar
    -0.06
    ±
    -0.06
    å®ŀåľ¨
    -0.06
    POSITIVE LOGITS
     |–
    0.08
    arend
    0.08
    à®°à®ļ
    0.07
    ricos
    0.07
    icator
    0.07
    vida
    0.07
    éģĵ
    0.07
    vid
    0.07
    ×Ļ×ķת
    0.07
    cky
    0.06
    Activations Density 0.013%

    No Known Activations