© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46468
    Prev
    Next
    INDEX
    Explanations

    better than

    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
    chter
    -0.08
    Verk
    -0.08
    abu
    -0.08
     ejemp
    -0.07
     رÙĤ
    -0.07
    /world
    -0.07
     ident
    -0.07
    au
    -0.07
    .Simple
    -0.07
    ôt
    -0.07
    POSITIVE LOGITS
    åĭī
    0.10
    åĭī强
    0.10
    éĹ´æİ¥
    0.10
    ëĤĺë§Ī
    0.09
    临
    0.09
     albeit
    0.09
     indirect
    0.08
     closest
    0.08
    æĹłå¥Ī
    0.08
    èĻ½çĦ¶æ²¡æľī
    0.08
    Activations Density 0.017%

    No Known Activations