© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23516
    Prev
    Next
    INDEX
    Explanations

    sorted sequence

    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
     Quay
    -0.07
     паÑĢи
    -0.07
    çŃĸ
    -0.07
    à¹Ĥà¸ŀ
    -0.07
    _KEEP
    -0.07
    oca
    -0.07
    大ä¹ī
    -0.07
    æĬķåħ¥
    -0.07
    zin
    -0.07
    çĶ¨å¿ĥåİ»
    -0.07
    POSITIVE LOGITS
     reorder
    0.10
     reordered
    0.10
     distribution
    0.08
    .sorted
    0.08
    æİĴåºı
    0.08
    åĪĨå¸ĥ
    0.08
    sorted
    0.08
     redistribution
    0.08
    ìĪľìľĦ
    0.07
    oren
    0.07
    Activations Density 0.003%

    No Known Activations