© 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. 55433
    Prev
    Next
    INDEX
    Explanations

    sequences and equations

    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
    éĤij
    -0.07
    /remove
    -0.07
    æ¢ĵ
    -0.06
     Gom
    -0.06
    ä¸ĢæľĽ
    -0.06
    æ°´äºķ
    -0.06
    igia
    -0.06
    INGK
    -0.06
    arno
    -0.06
    æķħéĩĮ
    -0.06
    POSITIVE LOGITS
    声
    0.08
     loose
    0.08
    æĬ
    0.08
    åĪºå®¢
    0.08
    幽幽
    0.07
    obble
    0.07
    æĸŃç»Ń
    0.07
    ood
    0.07
    .strict
    0.07
    åįģåĢį
    0.07
    Activations Density 0.208%

    No Known Activations