© 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. 9954
    Prev
    Next
    INDEX
    Explanations

    journal names and citations

    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
    бÑı
    -0.07
    迹
    -0.07
    gett
    -0.07
    æ¹ĸæ°´
    -0.07
     imp
    -0.07
    é£Ļ
    -0.07
    ×ŀ×ĵ
    -0.07
    çĶ¨æ°´
    -0.07
     continuous
    -0.06
    é±
    -0.06
    POSITIVE LOGITS
    æijĩæĻĥ
    0.08
    lai
    0.08
    uster
    0.08
    å¤ļçľĭ
    0.07
     Cit
    0.07
    Selectable
    0.07
    leet
    0.07
    åį«å£«
    0.07
     strconv
    0.07
    undle
    0.07
    Activations Density 0.004%

    No Known Activations