© 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. 38938
    Prev
    Next
    INDEX
    Explanations

    coding callouts

    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
    alm
    -0.10
    tores
    -0.08
    éĶµ
    -0.08
    为äºĨæıIJé«ĺ
    -0.07
    lade
    -0.07
    士å®ĺ
    -0.07
    estra
    -0.06
    湯
    -0.06
    áº
    -0.06
    (Optional
    -0.06
    POSITIVE LOGITS
    è¿Ľè¡Įæ¯Ķè¾ĥ
    0.08
    ç´įåħ¥
    0.07
     üzerinden
    0.07
    å½ĵä¹ĭ
    0.07
    说好
    0.07
    æĻĵ举
    0.07
     comparison
    0.07
    纳åħ¥
    0.07
    otas
    0.07
     med
    0.07
    Activations Density 0.077%

    No Known Activations