© 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. 56854
    Prev
    Next
    INDEX
    Explanations

    templateCode, templateName, templateKey

    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
    åį«ä¸ľ
    -0.08
    ocache
    -0.07
     Canh
    -0.07
    amil
    -0.07
    [ii
    -0.07
    cioni
    -0.07
    é£ĵé£İ
    -0.07
    VML
    -0.07
    ynie
    -0.06
    imon
    -0.06
    POSITIVE LOGITS
    大讲åłĤ
    0.08
    inder
    0.07
    Ùĩب
    0.06
    uez
    0.06
    åĩĨäºĪ
    0.06
    á»·
    0.06
    èĢģä¼´
    0.06
     Pearce
    0.06
    arang
    0.06
    jenigen
    0.06
    Activations Density 0.084%

    No Known Activations