© 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. 41429
    Prev
    Next
    INDEX
    Explanations

    file paths and code commands

    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
    eros
    -0.07
    æѦå¸Ŀ
    -0.06
    aylor
    -0.06
    è¦ģæ±Ĥ被åijĬ
    -0.06
    eras
    -0.06
    ons
    -0.06
    oth
    -0.06
    اÙĨ
    -0.06
    ves
    -0.06
    ä¸įåħ¥
    -0.06
    POSITIVE LOGITS
    éĹ
    0.08
    inel
    0.07
    ÏĢή
    0.07
     fileSize
    0.07
    paren
    0.07
    ä¸Ĭ好
    0.07
    çĥ
    0.07
    äh
    0.07
    CLU
    0.07
    CEE
    0.07
    Activations Density 0.328%

    No Known Activations