© 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. 3089
    Prev
    Next
    INDEX
    Explanations

    forall and every

    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
    åıĸåĨ³
    -0.08
    ppen
    -0.08
    ISTER
    -0.08
    ICLE
    -0.07
    favicon
    -0.07
    'class
    -0.07
    fen
    -0.07
    è¿Ļ次活åĬ¨
    -0.07
    derland
    -0.07
    dle
    -0.07
    POSITIVE LOGITS
    ivre
    0.07
    æĪĸ
    0.06
    ÙIJ
    0.06
    ä¸ĢåĪĩ
    0.06
    agnostics
    0.06
    对æīĢæľī
    0.06
    äºĨåIJĹ
    0.06
    agro
    0.06
     or
    0.06
    åĪļ
    0.06
    Activations Density 0.009%

    No Known Activations