© 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. 19059
    Prev
    Next
    INDEX
    Explanations

    numbers and website suffixes

    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
    迪äºļ
    -0.07
    acu
    -0.07
    ä¸ĢèĪ¬éľĢè¦ģ
    -0.07
    TML
    -0.07
    ä¸ĬçĻ¾
    -0.06
    ryw
    -0.06
     utk
    -0.06
    åı¹
    -0.06
    æĿł
    -0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.06
    POSITIVE LOGITS
    èµĦ
    0.09
    idata
    0.07
    åħĪåľ¨
    0.07
    梯
    0.07
    inox
    0.07
    osity
    0.07
    ä¹ħåĿIJ
    0.07
    rach
    0.06
    æį®
    0.06
    ungsver
    0.06
    Activations Density 0.003%

    No Known Activations