© 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. 62385
    Prev
    Next
    INDEX
    Explanations

    follow up to

    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
    ä¸į移
    -0.07
    mps
    -0.07
    æľ¬åĵģ
    -0.07
    ozn
    -0.07
    gaard
    -0.07
    weights
    -0.06
    à¸ĩ
    -0.06
    ãĥıãĤ¤
    -0.06
    ussi
    -0.06
    hand
    -0.06
    POSITIVE LOGITS
    åĩºåı£çļĦ
    0.08
    åĪļæīį
    0.08
    ä¸ĬéĿ¢çļĦ
    0.07
    è¿Ŀåıįä¸Ĭè¿°
    0.07
    主é¢ĺ
    0.07
    æĸ¹æīį
    0.07
    对ä¸Ĭè¿°
    0.07
    åīįéĿ¢çļĦ
    0.07
    éĤ£åı¥
    0.07
    æīĢè¿°çļĦ
    0.07
    Activations Density 0.199%

    No Known Activations