© 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. 65218
    Prev
    Next
    INDEX
    Explanations

    section separators

    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
    alar
    -0.09
    ught
    -0.09
    å°ıæĿ¿
    -0.08
    è¿IJè¡ĮæŶ
    -0.08
    è¿IJè¡ĮçļĦ
    -0.08
    onta
    -0.08
    è¿ŀäºij
    -0.08
    board
    -0.08
    åĴĮè§Ĩé¢ij
    -0.08
    ÙĪÙĤÙĬ
    -0.08
    POSITIVE LOGITS
    æĻĵæĺİ
    0.06
    blem
    0.06
    çĻ»è®°æīĭç»Ń
    0.06
    0.06
    人
    0.05
    Ĭ
    0.05
    åĭĺ
    0.05
    ĥ
    0.05
    ู
    0.05
    çĤ³
    0.05
    Activations Density 0.004%

    No Known Activations