© 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. 8134
    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
    ç»Ļ大家æݨèįIJ
    -0.09
    eut
    -0.09
    èı²å°Ķå¾·
    -0.09
    ç´§åĩijåŀĭ
    -0.08
    (Void
    -0.08
     YYS
    -0.08
    olec
    -0.08
    ç«£
    -0.08
    _COMPLEX
    -0.08
    èī°
    -0.08
    POSITIVE LOGITS
     systematic
    0.08
     worst
    0.08
    æł¹æºIJ
    0.08
     noise
    0.08
     affecting
    0.08
     random
    0.08
     sources
    0.07
     harmless
    0.07
     inflicted
    0.07
     residual
    0.07
    Activations Density 0.034%

    No Known Activations