© 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. 19093
    Prev
    Next
    INDEX
    Explanations

    Q ratio

    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
     anthrop
    -0.08
    åľ¨çľī
    -0.07
    é²ľèĤī
    -0.07
    anne
    -0.07
    &C
    -0.07
     soup
    -0.07
    è¡ĮæĶ¿å¤Ħç½ļ
    -0.07
    onge
    -0.07
    filesize
    -0.07
    &r
    -0.07
    POSITIVE LOGITS
    yll
    0.08
    imuth
    0.07
    æ»ĭåħ»
    0.07
    æŀķ
    0.07
    ç«ĭ交
    0.07
    åħ¬æľīåĪ¶
    0.06
    erry
    0.06
    ê
    0.06
    äºĴéĢļ
    0.06
    çĬ
    0.06
    Activations Density 0.002%

    No Known Activations