© 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. 34101
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    enet
    -0.11
    æľĢæĸ°è¯Ħ论
    -0.08
    annes
    -0.07
    linik
    -0.07
    plice
    -0.07
    Åijbb
    -0.07
    .Fore
    -0.07
    enia
    -0.07
    egner
    -0.07
    avers
    -0.07
    POSITIVE LOGITS
    ville
    0.07
    绣
    0.07
    berry
    0.06
    è·¯
    0.06
    ä¸įèµ·
    0.06
    omen
    0.06
    æ¯ĶæĪij们
    0.06
    ën
    0.06
    鼶
    0.06
    人éģĵ
    0.06
    Activations Density 0.006%

    No Known Activations