© 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. 19916
    Prev
    Next
    INDEX
    Explanations

    consideration allows

    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
    eil
    -0.07
    Plain
    -0.07
     COPYRIGHT
    -0.06
    çIJĨè®ºçŁ¥è¯Ĩ
    -0.06
     physically
    -0.06
    æĹ¥æĬ¥
    -0.06
    åĪĢ
    -0.06
    fly
    -0.06
    agram
    -0.06
    åıªæľīéĢļè¿ĩ
    -0.06
    POSITIVE LOGITS
    åı¯èĥ½å¯¼èĩ´
    0.09
    ä¼ļ导èĩ´
    0.09
    ä¹Łä¼ļ导èĩ´
    0.09
    åı¯èĥ½ä¼ļ导èĩ´
    0.08
     recal
    0.08
    åĴ¨
    0.08
    导èĩ´
    0.08
     would
    0.08
    leads
    0.08
    vens
    0.08
    Activations Density 0.010%

    No Known Activations