© 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. 26310
    Prev
    Next
    INDEX
    Explanations

    legal casing

    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
    agre
    -0.08
    ane
    -0.08
     ctype
    -0.07
    hum
    -0.07
    Stroke
    -0.07
    æĥ³èµ·äºĨ
    -0.07
    ardu
    -0.07
    nip
    -0.07
    اÙĬ
    -0.07
    ANE
    -0.06
    POSITIVE LOGITS
    ä¼°
    0.07
    tel
    0.06
    å¼ĢæĿ¥
    0.06
    åĬŀæ³ķ
    0.06
    ÐĴа
    0.06
    éĩijéĻµ
    0.06
     resi
    0.06
    .Est
    0.06
    æĺİçıł
    0.06
    æ¿®
    0.06
    Activations Density 0.026%

    No Known Activations