© 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. 24477
    Prev
    Next
    INDEX
    Explanations

    `test` commands and related flags

    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
    ocz
    -0.07
    FILENAME
    -0.07
    stoff
    -0.06
    è°Īå¿ĥ
    -0.06
    ogra
    -0.06
    åŁºéĥ¨
    -0.06
    æŃ¦å£«
    -0.06
    Ù°
    -0.06
    è¿Ļç§įäºĭæĥħ
    -0.06
    æŃ¹
    -0.06
    POSITIVE LOGITS
    æĭĽ
    0.08
    imity
    0.08
    ä¸ĭåĪ°
    0.07
    ç¯Ļ
    0.07
    rec
    0.07
    ellen
    0.07
    æĥľ
    0.07
    aky
    0.07
    èĪį
    0.07
    iven
    0.06
    Activations Density 0.004%

    No Known Activations