© 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. 45653
    Prev
    Next
    INDEX
    Explanations

    method or approach

    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
    echt
    -0.08
     ::=
    -0.08
    ä¸įèĥ½ä½ľä¸º
    -0.07
    ä¸įåºĶæ±Ĥ
    -0.07
    ingend
    -0.07
    ->$
    -0.07
    ANGE
    -0.07
    iecz
    -0.07
    IBC
    -0.07
    camel
    -0.07
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹æ³ķ
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.09
    çļĦä¼ĺçĤ¹
    0.08
    fte
    0.08
     method
    0.08
    éģ¿åħįäºĨ
    0.07
     yields
    0.07
     avoids
    0.07
     approach
    0.07
    缺çĤ¹æĺ¯
    0.07
    Activations Density 0.105%

    No Known Activations