© 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. 45657
    Prev
    Next
    INDEX
    Explanations

    Let calculations after punctuation

    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
    кÑĬ
    -0.08
    xab
    -0.08
     Bit
    -0.07
    istra
    -0.07
    ç«¥åŃIJ
    -0.07
    çĦ¶æĺ¯
    -0.07
    opot
    -0.06
    bit
    -0.06
    åĬłåĭĴ
    -0.06
    ¼
    -0.06
    POSITIVE LOGITS
    ESCO
    0.07
    Assignable
    0.07
    à¸ĺุ
    0.07
    ikkan
    0.07
    inz
    0.07
    æīĵåľ¨
    0.07
    éĤ£ä¸Ģ天
    0.07
     Constit
    0.07
    åľ¨æĪijå¿ĥä¸Ń
    0.07
    ä¸Ģä¸ĭå°±
    0.06
    Activations Density 0.002%

    No Known Activations