© 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. 26212
    Prev
    Next
    INDEX
    Explanations

    UiImageView, UiButton, Ri-my, Chansu-gargarizan, TEDX, Twining Tea, Myers-Briggs, Pomatoceros lamarkii, Rift Valley virus

    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
    sembly
    -0.09
    ÑĪÑĮ
    -0.08
    orea
    -0.08
    yleft
    -0.08
    ä¸ĢçĦ¡
    -0.08
    -vs
    -0.08
    åĽ¾æĸ¯
    -0.08
     **:**
    -0.08
    .nih
    -0.08
    ukat
    -0.08
    POSITIVE LOGITS
    irn
    0.07
    æĺ¨å¤©çļĦ
    0.06
    ......
    0.06
    ارد
    0.06
    ite
    0.06
    ....
    0.06
    iton
    0.06
    cia
    0.06
    ----
    0.06
     sur
    0.06
    Activations Density 1.781%

    No Known Activations