© 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. 60478
    Prev
    Next
    INDEX
    Explanations

    residual quantization

    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
    çİīæłij
    -0.09
    å¹²äºĭ
    -0.07
    åīijæ°Ķ
    -0.07
     lau
    -0.07
     Gim
    -0.07
    oser
    -0.06
    ÏĨη
    -0.06
    /email
    -0.06
     Mirage
    -0.06
    pon
    -0.06
    POSITIVE LOGITS
     kef
    0.09
    ucch
    0.08
    ogne
    0.07
    IGNAL
    0.07
    resa
    0.07
    å°ıå¹³
    0.07
     ë³ĦëıĦ
    0.07
    tac
    0.07
     Ñĥв
    0.07
    łĢ
    0.07
    Activations Density 0.234%

    No Known Activations