© 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. 51003
    Prev
    Next
    INDEX
    Explanations

    unstable procedures, flight, proteasome, lizards

    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
    å¨ĺ家
    -0.08
    éĢĬ
    -0.08
    èł
    -0.07
    æľ¬å¹³åı°
    -0.06
    Mesh
    -0.06
    Aws
    -0.06
    ede
    -0.06
     mesh
    -0.06
     nurs
    -0.06
    éĺ¿éĩĮå·´å·´
    -0.06
    POSITIVE LOGITS
    zenÃŃ
    0.08
    ogli
    0.08
    举个
    0.08
    lass
    0.08
    strup
    0.08
    ä¾ĭ
    0.07
    ä¾ĭåŃIJ
    0.07
     example
    0.07
    çļĦä¾ĭåŃIJ
    0.07
    为ä¾ĭ
    0.07
    Activations Density 0.371%

    No Known Activations