© 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. 41481
    Prev
    Next
    INDEX
    Explanations

    defining conditions or methods

    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
    jat
    -0.08
    arks
    -0.08
    inski
    -0.07
    _padding
    -0.07
    ä¾µçĬ¯æĤ¨çļĦ
    -0.07
    对该
    -0.07
    à¹Ģà¸Ľà¹ĩà¸Ļสิà¹Īà¸ĩ
    -0.07
    iras
    -0.07
    æĺ¯è¯¥
    -0.07
    ÑıÑĤи
    -0.07
    POSITIVE LOGITS
     whereby
    0.11
    éĢļè¿ĩå°Ĩ
    0.09
     wherein
    0.09
     waarbij
    0.08
     poleg
    0.08
    å°Ĩä¸Ģ个
    0.07
    éĢļè¿ĩåľ¨
    0.07
    strup
    0.07
    leich
    0.07
    /method
    0.07
    Activations Density 0.183%

    No Known Activations