© 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. 19439
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific parameters

    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
    æĪĸéĥ¨åĪĨ
    -0.08
    our
    -0.06
    _startup
    -0.06
    èĹ
    -0.06
    æłijä¸Ģ
    -0.06
    æĪĸèĢħæľī
    -0.06
    æĪĸçĶ±
    -0.06
    æĪĸåĽł
    -0.06
    äºĮè¯Ŀ
    -0.06
    oral
    -0.06
    POSITIVE LOGITS
    itty
    0.08
    à¹ģละà¸Ħวาม
    0.08
    occo
    0.07
    å°±çŁ¥éģĵäºĨ
    0.07
    è¶ħåīį
    0.07
     táºŃt
    0.07
    çİĩåĴĮ
    0.07
    æĶ¯
    0.07
    irs
    0.07
    ãĢģ
    0.07
    Activations Density 0.008%

    No Known Activations