© 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. 49476
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    æĪ¿åľ°
    -0.07
     Gedanken
    -0.07
    æľ¬åľ°åĮº
    -0.07
    æīĵä¸Ĭ
    -0.07
    家éŨåı£
    -0.07
    ra
    -0.07
    loff
    -0.07
    æĥ³æ³ķ
    -0.06
    à¹Ģหม
    -0.06
    abouts
    -0.06
    POSITIVE LOGITS
    好å¿ĥ
    0.07
    lege
    0.07
    esm
    0.06
    heb
    0.06
    èı
    0.06
    æIJŃ
    0.06
     recul
    0.06
    .pin
    0.06
    ä»ĺæģ¯
    0.06
    ëĭĿ
    0.06
    Activations Density 0.003%

    No Known Activations