© 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. 57947
    Prev
    Next
    INDEX
    Explanations

    index assignment

    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
    èvre
    -0.08
    çIJĨæīĢ
    -0.07
    co
    -0.07
    éĶĻè¿ĩçļĦ
    -0.07
    amu
    -0.07
    he
    -0.07
    zb
    -0.07
     Volg
    -0.07
    æŶæīĢ
    -0.06
    ä¸ĢèĦī
    -0.06
    POSITIVE LOGITS
    ]]=
    0.08
    ä¸įèĻļ
    0.08
    alars
    0.07
    çļĦéĹ®é¢ĺæĺ¯
    0.07
    iable
    0.07
    etil
    0.07
    dens
    0.07
     &=
    0.07
    ç½²
    0.06
    çī¹éĩĮ
    0.06
    Activations Density 0.017%

    No Known Activations