© 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. 9526
    Prev
    Next
    INDEX
    Explanations

    numbers after opening parenthesis

    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
    ائ
    -0.07
    åĪ«æľī
    -0.06
    èİ«
    -0.06
    åĵŃ声
    -0.06
    oren
    -0.06
    åıĻè¿°
    -0.06
     Avis
    -0.06
    æľīæĥħ
    -0.06
    çĤ¹åĩ»ä¸Ĭæĸ¹
    -0.06
    çļİ
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĤ«ãĥ¼
    0.08
    enhagen
    0.08
    _GP
    0.07
    agia
    0.07
    antry
    0.07
    egah
    0.07
    _HIDE
    0.07
    orthy
    0.07
    ãĥ¼ãĥŀ
    0.07
    anton
    0.07
    Activations Density 0.164%

    No Known Activations