© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49936
    Prev
    Next
    INDEX
    Explanations

    world

    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
    fors
    -0.07
    CK
    -0.07
    uet
    -0.07
    æľī礼
    -0.06
    æĸ°çĶŁçļĦ
    -0.06
    uffs
    -0.06
    ä¸įè¡Į
    -0.06
    sd
    -0.06
    amt
    -0.06
    édi
    -0.06
    POSITIVE LOGITS
    JET
    0.08
    polis
    0.07
    à¸Ħำà¸Ļว
    0.07
    [âĢ¦
    0.07
    æĿ¥èĩªç½ij绾
    0.06
    åħ¸èĹı
    0.06
    ricos
    0.06
    __[
    0.06
    illian
    0.06
    ÑĤÑĩ
    0.06
    Activations Density 0.538%

    No Known Activations