© 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. 47443
    Prev
    Next
    INDEX
    Explanations

    _table

    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
    纳æĸ¯
    -0.08
    æĮijæĪĺæĢ§
    -0.08
    ELLOW
    -0.08
    éĩį温
    -0.08
    oley
    -0.08
    à¸ķั
    -0.08
    orny
    -0.07
     cá»±
    -0.07
    fahren
    -0.07
    èĩªæŁ¥
    -0.07
    POSITIVE LOGITS
    èĢķåľ°
    0.07
    å©Ģ
    0.06
    _yaml
    0.06
     Gael
    0.06
    çľĭå¾Ĺ
    0.06
    isma
    0.06
    essim
    0.06
    peÄį
    0.06
     bios
    0.06
    æ¯Ľ
    0.06
    Activations Density 0.009%

    No Known Activations