© 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. 21442
    Prev
    Next
    INDEX
    Explanations

    number format and calculation

    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
    濯
    -0.07
    enis
    -0.07
    dden
    -0.07
    æĢĿç»´èĥ½åĬĽ
    -0.07
     mysteries
    -0.07
    -compatible
    -0.06
    estad
    -0.06
    _DECLARE
    -0.06
    çİ®
    -0.06
     eid
    -0.06
    POSITIVE LOGITS
    è¶ħåĩºäºĨ
    0.09
     exceeds
    0.09
    è¶ħåĩº
    0.08
     exceed
    0.08
    ateur
    0.08
     exceeding
    0.08
    anski
    0.07
    adak
    0.07
     exceeded
    0.07
    è¶ħè¿ĩäºĨ
    0.07
    Activations Density 0.024%

    No Known Activations