© 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. 26553
    Prev
    Next
    INDEX
    Explanations

    noise and errors

    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
    缸继
    -0.08
    ayload
    -0.08
    æĸ¹ä¾¿çļĦ
    -0.08
     quadri
    -0.08
     stagger
    -0.08
     unthinkable
    -0.08
    çī¹æ®ĬçļĦ
    -0.07
     protokol
    -0.07
     двой
    -0.07
    è¿IJéĢģ
    -0.07
    POSITIVE LOGITS
     smoothing
    0.10
     noisy
    0.10
     noise
    0.08
    稳åģ¥
    0.08
     unbiased
    0.08
     outliers
    0.08
    éĩį建
    0.08
    å¹³æ»ij
    0.08
     penal
    0.07
    noise
    0.07
    Activations Density 0.045%

    No Known Activations