© 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. 22912
    Prev
    Next
    INDEX
    Explanations

    HTML Cleaner, Notebook Rest API, demand pull, Rserve

    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
    âĸ½
    -0.06
    _collection
    -0.06
    ahlen
    -0.06
    ounds
    -0.06
    appers
    -0.06
    chung
    -0.06
    hares
    -0.06
    AY
    -0.05
    endes
    -0.05
    corre
    -0.05
    POSITIVE LOGITS
    æľ¬èº«å°±æĺ¯
    0.10
    æľ¬èº«å°±
    0.10
     vs
    0.09
    ä¹ĭåĪĥ
    0.09
    çļĦåħ¶ä»ĸ
    0.09
    ä¸Ģç«ł
    0.08
     versus
    0.08
    èĻ½å°ı
    0.08
    æľ¬æĿ¥å°±æĺ¯
    0.08
    çļĦ大å¹ħ
    0.08
    Activations Density 0.007%

    No Known Activations