© 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. 8467
    Prev
    Next
    INDEX
    Explanations

    new cultiv

    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
    æī¯
    -0.08
    æIJŀ好
    -0.08
     rẽ
    -0.07
    Ñģев
    -0.07
    å°±ä¼ļæľī
    -0.07
    orton
    -0.06
    è¿ĩ好
    -0.06
    驶
    -0.06
    ä¸ĭä¸Ģ页
    -0.06
    ably
    -0.06
    POSITIVE LOGITS
    enci
    0.09
    irman
    0.07
    version
    0.07
    rott
    0.07
     version
    0.07
    è¡·å¿ĥçļĦ
    0.07
    acr
    0.07
    èĴ¸èĴ¸
    0.07
     Bau
    0.07
    reau
    0.07
    Activations Density 0.003%

    No Known Activations