© 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. 24893
    Prev
    Next
    INDEX
    Explanations

    day titles

    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
    irection
    -0.09
    eley
    -0.07
    éĩij马
    -0.07
    ¹Ħ
    -0.07
    ÑĢана
    -0.07
    angani
    -0.07
    áŀ½
    -0.07
    aisu
    -0.07
    åİŁæĿ¥æĺ¯
    -0.07
    ëł¹
    -0.07
    POSITIVE LOGITS
    egal
    0.07
    æĤ£
    0.07
    andar
    0.07
    èģļ
    0.07
    æ°ij
    0.07
    åłµ
    0.07
    ffi
    0.07
    æĸ¹æ³ķçļĦ
    0.07
    主人
    0.07
    .runtime
    0.07
    Activations Density 0.095%

    No Known Activations