© 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. 14461
    Prev
    Next
    INDEX
    Explanations

    statistical measures and comparisons

    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
    ä¸Ģä½ĵçļĦ
    -0.09
    å¦į
    -0.08
    .sendStatus
    -0.08
     (!((
    -0.08
    éĵ¿
    -0.08
    åħįè´¹éĺħ读
    -0.08
    宿
    -0.07
    DebugEnabled
    -0.07
    _gp
    -0.07
    æĺİä¿¡
    -0.07
    POSITIVE LOGITS
     weighted
    0.09
     weighting
    0.09
    weighted
    0.08
     dataset
    0.08
     summed
    0.08
    åľ¨æ¯ı个
    0.08
     averaged
    0.08
     statistically
    0.07
     outlier
    0.07
    alan
    0.07
    Activations Density 0.050%

    No Known Activations