© 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. 58276
    Prev
    Next
    INDEX
    Explanations

    re- prefix followed by words

    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
    kem
    -0.08
    retrieve
    -0.08
    æŀģäºĨ
    -0.07
     adjunct
    -0.07
    odor
    -0.06
    æľĢæĸ°æĽ´æĸ°
    -0.06
    ¡´
    -0.06
    ä¹ĭæľĢ
    -0.06
     deed
    -0.06
    è¿Ħä»Ĭ
    -0.06
    POSITIVE LOGITS
    /ref
    0.11
    äºĨä¸Ģéģį
    0.10
    entrant
    0.09
    /re
    0.09
    ä¸Ģéģį
    0.09
    åĴĮè°ĥæķ´
    0.09
    /up
    0.09
    foundland
    0.09
    /rec
    0.09
    æĹĹé¼ĵ
    0.08
    Activations Density 0.192%

    No Known Activations