© 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. 33007
    Prev
    Next
    INDEX
    Explanations

    disabled, disable, or non-working

    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
    ogne
    -0.07
    emn
    -0.07
    æ¯ı天æĹ©ä¸Ĭ
    -0.07
    Ī¬
    -0.07
    ufs
    -0.07
    ynd
    -0.07
    ัà¹īà¸ĩ
    -0.07
    BTN
    -0.07
    奶çĪ¸
    -0.07
    ook
    -0.07
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.07
    èĻ½æľī
    0.07
    è¿Ľåİ»
    0.07
    tw
    0.07
    ä¸Ģå¾ĭ
    0.06
    è¯ķä¸Ģè¯ķ
    0.06
    jamin
    0.06
     prohib
    0.06
    ÙİØŃ
    0.06
    æĻ®éĢļè¯Ŀ
    0.06
    Activations Density 0.018%

    No Known Activations