© 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. 65488
    Prev
    Next
    INDEX
    Explanations

    real numbers

    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
    åĩºäºĭ
    -0.08
    θεν
    -0.08
    {{{
    -0.07
    CREMENT
    -0.07
    ovin
    -0.07
    egas
    -0.07
    åĢįå¢ŀ
    -0.07
    éĿŀ常é«ĺ
    -0.07
    åį³çĶ¨
    -0.07
    igur
    -0.07
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.09
    çĶļèĩ³
    0.07
    çĶļèĩ³äºİ
    0.07
    ised
    0.07
    eras
    0.07
    -val
    0.07
    orp
    0.06
    åĩ¡
    0.06
    aise
    0.06
    çĶļèĩ³æĺ¯
    0.06
    Activations Density 0.006%

    No Known Activations