© 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. 19617
    Prev
    Next
    INDEX
    Explanations

    numerical calculation and analysis

    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
    оÑĢод
    -0.10
    ippe
    -0.07
    è¶Ĭéķ¿
    -0.07
    Ñįй
    -0.07
    ehr
    -0.07
     terecht
    -0.07
     altrett
    -0.07
    èIJ¥ä¸ļ
    -0.07
    æģĭ人
    -0.07
    ech
    -0.07
    POSITIVE LOGITS
    åľ¨åħ·ä½ĵ
    0.10
     numerical
    0.09
    æķ°åĢ¼
    0.09
     numeric
    0.08
     values
    0.08
    _specific
    0.08
    代åħ¥
    0.08
    åħ·ä½ĵçļĦ
    0.08
     Numer
    0.08
    åħ·ä½ĵçļĦãģª
    0.08
    Activations Density 0.032%

    No Known Activations