© 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. 31152
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    大åIJĥ
    -0.06
    avas
    -0.06
     Vu
    -0.06
    使çĶ¨çļĦ
    -0.06
    unix
    -0.06
     tand
    -0.05
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    -0.05
    ết
    -0.05
    æĸ½
    -0.05
    صØŃ
    -0.05
    POSITIVE LOGITS
    ToEnd
    0.08
    代人
    0.08
     //{
    0.08
     ÑĥÑĢав
    0.08
    Selector
    0.08
    renc
    0.07
    Ùģعة
    0.07
    essus
    0.07
    ниÑĨ
    0.07
    .son
    0.07
    Activations Density 0.025%

    No Known Activations