© 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. 49450
    Prev
    Next
    INDEX
    Explanations

    pros, cons, comments

    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
     such
    -0.06
    wise
    -0.06
    ,
    -0.06
     specific
    -0.06
    ***
    -0.06
    -0.06
     relevant
    -0.06
    اتÛĮ
    -0.06
    æľīæѤ
    -0.05
    iser
    -0.05
    POSITIVE LOGITS
     cú
    0.08
    pll
    0.08
    hek
    0.08
    èĤ¯å®ļæĺ¯
    0.08
     Favor
    0.08
    favor
    0.08
    è¿Ŀåıįä¸Ĭè¿°
    0.08
    åı£èĩŃ
    0.08
    以ä¸Ĭæĺ¯
    0.08
     Ñĩи
    0.08
    Activations Density 0.051%

    No Known Activations