© 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. 14656
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    è§Ĩéķľ
    -0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    nest
    -0.07
    abe
    -0.07
    antu
    -0.07
    atchet
    -0.06
    ืà¸Ļ
    -0.06
    ibo
    -0.06
    -money
    -0.06
    æĹłèĻij
    -0.06
    POSITIVE LOGITS
    nud
    0.07
    æ¾Ħ
    0.07
    arendra
    0.07
    å¾Ĺåĩºç»ĵ论
    0.07
    puter
    0.07
    orro
    0.07
    odoro
    0.07
    alama
    0.07
    ÑĪкаÑħ
    0.07
    OrElse
    0.06
    Activations Density 0.007%

    No Known Activations