© 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. 13740
    Prev
    Next
    INDEX
    Explanations

    example

    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
     either
    -0.08
    '
    -0.07
    ^
    -0.07
    _
    -0.07
    è¦ģä¹Ī
    -0.06
    —
    -0.06
    缸åºĶçļĦ
    -0.06
    -
    -0.06
    /
    -0.06
    |
    -0.06
    POSITIVE LOGITS
    æŁIJåĢĭ
    0.11
    ampur
    0.11
    æŁIJä¸Ģ天
    0.10
    æŁIJ个
    0.10
    çĤºä¾ĭ
    0.10
    æŁIJçļĦ
    0.09
    aiss
    0.09
    æŁIJ
    0.09
    chten
    0.09
    ä¸Ģ家ä¸īåı£
    0.09
    Activations Density 0.034%

    No Known Activations