© 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. 57319
    Prev
    Next
    INDEX
    Explanations

    compared to/with

    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
    assi
    -0.08
    ellis
    -0.08
    ellation
    -0.07
    olson
    -0.07
    èĢĮèĩªå·±
    -0.07
    äººä¸ºæľ¬
    -0.07
    lords
    -0.07
    abby
    -0.07
    åĬªåĬĽæĬĬ
    -0.07
    èves
    -0.07
    POSITIVE LOGITS
    äºİ
    0.10
    à¸ģัà¸ļ
    0.08
    ä¸İåħ¶
    0.08
    oth
    0.08
    åIJĮ
    0.07
    าà¸ģัà¸ļ
    0.07
    orting
    0.07
    ä¸İ
    0.07
    åľ°ä¸İ
    0.07
    irit
    0.07
    Activations Density 0.150%

    No Known Activations