© 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. 26739
    Prev
    Next
    INDEX
    Explanations

    experimental control 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
    y
    -0.07
    æĺ¥åįİ
    -0.06
    æ¡Ī
    -0.06
    çIJĨ论ä¸İ
    -0.06
    usc
    -0.06
    åıij
    -0.06
     Guer
    -0.06
    k
    -0.06
    à¸ĩ
    -0.06
     statement
    -0.06
    POSITIVE LOGITS
    对çħ§ç»Ħ
    0.12
    æĹłå¼Ĥ
    0.09
    对çħ§
    0.09
    controls
    0.09
     baseline
    0.09
    baseline
    0.09
    åIJĮæľŁ
    0.09
    Baseline
    0.08
    åIJĮæľŁçļĦ
    0.08
    çļĦæŃ£å¸¸
    0.08
    Activations Density 0.421%

    No Known Activations