© 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. 25771
    Prev
    Next
    INDEX
    Explanations

    enclosing punctuation or delimiters

    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
    osing
    -0.07
    æĬĦæĬ¥
    -0.06
    min
    -0.06
    åĿıä¹łæĥ¯
    -0.06
    å®ļçIJĨ
    -0.06
    urable
    -0.06
    ľ
    -0.06
    ewnÄħ
    -0.06
    ike
    -0.06
    fact
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.08
    ä¸İæľ¬ç«Ļ
    0.08
    resher
    0.07
    á»ķng
    0.07
     rám
    0.07
    itarian
    0.07
    çĻ¾äºĭ
    0.07
    çĤ¹åĩ»ä¸Ĭæĸ¹
    0.07
    å±ħ士
    0.07
    airo
    0.07
    Activations Density 0.008%

    No Known Activations