© 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. 57553
    Prev
    Next
    INDEX
    Explanations

    shapes and forms

    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
    uck
    -0.08
    夹å±Ĥ
    -0.08
    åħħæĸ¥
    -0.08
    kaan
    -0.07
    ä»ĩ
    -0.07
     subscript
    -0.07
     Rewrite
    -0.07
    umba
    -0.07
    UCK
    -0.07
    tones
    -0.07
    POSITIVE LOGITS
    å½¢çĬ¶çļĦ
    0.10
    å½¢çĬ¶
    0.10
    çļĦå½¢çĬ¶
    0.10
     모ìĸij
    0.09
     shape
    0.09
     shapes
    0.09
    åĽ¾æ¡Ī
    0.09
    å½¢çļĦ
    0.09
     patterns
    0.08
    shape
    0.08
    Activations Density 0.025%

    No Known Activations