© 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. 42086
    Prev
    Next
    INDEX
    Explanations

    standard deviation and limits of agreement

    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¸ŃåŃĹ
    -0.08
    åĩıç¨İ
    -0.07
    çĥģ
    -0.07
    ç³ľ
    -0.07
    æĸ
    -0.07
    çİĭ家
    -0.07
    .basename
    -0.07
    пле
    -0.07
    éĩįéĩıè½»
    -0.07
    解æ¯Ĵ
    -0.07
    POSITIVE LOGITS
    vier
    0.07
     outliers
    0.07
     STANDARD
    0.07
    å¹³æĹ¥
    0.07
    .standard
    0.07
    _EXCEPTION
    0.07
    æĤłæĤł
    0.07
    å¹ħ
    0.07
     violations
    0.07
    åįģæĿ¡
    0.07
    Activations Density 0.006%

    No Known Activations