© 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. 47685
    Prev
    Next
    INDEX
    Explanations

    mathematical criteria or conditions

    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
    æĺ¯æīĢæľī
    -0.07
    olla
    -0.07
    imized
    -0.07
    缤
    -0.07
    mue
    -0.07
    éĻ¢æīĢ
    -0.07
     pen
    -0.06
    isi
    -0.06
    æĬĬæīĢæľī
    -0.06
    umed
    -0.06
    POSITIVE LOGITS
     criteria
    0.12
     Criteria
    0.12
     Criterion
    0.12
    Criteria
    0.12
    Criterion
    0.11
     criterion
    0.11
     Kriter
    0.10
     criter
    0.10
    æĿ¡ä»¶
    0.10
     Kriterien
    0.10
    Activations Density 0.016%

    No Known Activations