© 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. 50957
    Prev
    Next
    INDEX
    Explanations

    purpose statement

    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
    æľīä¸īç§į
    -0.09
    æľī两ç§į
    -0.08
    æľīäºĮ
    -0.08
     Reinh
    -0.07
    /animations
    -0.07
    å°¸
    -0.07
    igan
    -0.07
    æľī两个
    -0.06
    å¾Ģä¸Ĭ
    -0.06
    ä¸įæĹ©
    -0.06
    POSITIVE LOGITS
     rewritten
    0.09
    äºĭ项çļĦ
    0.07
    aved
    0.07
     áĥIJáĥ¦
    0.07
     corrid
    0.07
    ä¸ĭè¿°
    0.07
     pÄģr
    0.07
    besch
    0.07
     Gda
    0.07
     Rewrite
    0.07
    Activations Density 0.008%

    No Known Activations