© 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. 42147
    Prev
    Next
    INDEX
    Explanations

    optimization objective function

    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
    èµĦè´¨çļĦ
    -0.06
    acap
    -0.06
    dings
    -0.06
    è¿Ļ群
    -0.06
    ÑĤок
    -0.06
    æ§Ľ
    -0.06
    交éĢļå·¥åħ·
    -0.06
    解æĥij
    -0.06
    ãĤį
    -0.06
    æĥĬéŃĤ
    -0.06
    POSITIVE LOGITS
    æĥ©ç½ļ
    0.11
     penal
    0.11
     reward
    0.11
     penalty
    0.10
     penalties
    0.10
     rewards
    0.10
    ç½ļ
    0.10
     weights
    0.10
     weight
    0.09
     Weight
    0.09
    Activations Density 0.031%

    No Known Activations