© 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. 3629
    Prev
    Next
    INDEX
    Explanations

    VisualBoyAdvance emulator

    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
    arly
    -0.07
    ogramm
    -0.07
    oup
    -0.06
    æĿ¿ä¸Ĭ
    -0.06
    åĽ½åįİ
    -0.06
    被æĪij
    -0.06
    aps
    -0.06
    æ¯Ķçī¹
    -0.06
    è¾Ī
    -0.06
    åĪ¶
    -0.06
    POSITIVE LOGITS
     oci
    0.08
    ç»İ
    0.08
    ebes
    0.08
    è¿IJ
    0.08
    ngle
    0.08
    [::-
    0.07
    ä¿Ĭ
    0.07
    WithOptions
    0.07
    -fw
    0.07
    lamento
    0.07
    Activations Density 0.198%

    No Known Activations