© 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. 31354
    Prev
    Next
    INDEX
    Explanations

    units of measure or segments

    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
    cem
    -0.07
    åİ®
    -0.07
    ewise
    -0.07
    èĩªå¾Ĺ
    -0.07
     resa
    -0.06
    éĢĤ
    -0.06
    对æĸ°
    -0.06
    æīĭ
    -0.06
    kar
    -0.06
    天人
    -0.06
    POSITIVE LOGITS
    éĢļ常为
    0.09
     subdivisions
    0.09
    åĽºå®ļ
    0.08
    æłĩåĩĨ为
    0.08
    Mutable
    0.08
    -standard
    0.08
    åĪĨ为
    0.08
    ç»ĦæĪIJ
    0.08
    åĽºå®ļçļĦ
    0.08
     divisions
    0.08
    Activations Density 0.023%

    No Known Activations