© 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. 65523
    Prev
    Next
    INDEX
    Explanations

    length grows logarithmically

    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
    éĢļè¿ĩè¿Ļ次
    -0.06
    ,None
    -0.06
    пок
    -0.06
    cope
    -0.06
    >/<
    -0.06
    Âł
    -0.06
    ä¸įæ¶īåıĬ
    -0.06
    缸åIJĮ
    -0.06
    ä¸Ķä¸į
    -0.06
    bene
    -0.06
    POSITIVE LOGITS
     roughly
    0.10
    大约æĺ¯
    0.09
    大æ¦Ĥåľ¨
    0.09
     dominated
    0.09
     asympt
    0.09
    大èĩ´
    0.09
    大约
    0.09
    dou
    0.08
     grows
    0.08
    essim
    0.08
    Activations Density 0.004%

    No Known Activations