© 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. 10152
    Prev
    Next
    INDEX
    Explanations

    system-wide

    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
    èĶ¼
    -0.07
    å¤ķ
    -0.07
    á»ĩ
    -0.07
    幸ç¦ıå¿«ä¹IJ
    -0.06
    ttp
    -0.06
    zeich
    -0.06
    Existing
    -0.06
     näch
    -0.06
    ÑıÑĤÑĮ
    -0.06
    خش
    -0.06
    POSITIVE LOGITS
    -,
    0.08
    èĩªå·±çļĦè¡Į为
    0.08
    mier
    0.07
    arre
    0.07
    »
    0.07
    igos
    0.07
    ogne
    0.07
    ä¹ĭæģĭ
    0.07
    rames
    0.07
    å½ĵçĦ¶è¦ģ
    0.07
    Activations Density 0.111%

    No Known Activations