© 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. 1476
    Prev
    Next
    INDEX
    Explanations

    Sierpinsky, fractals, Apollonian networks

    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
    omos
    -0.09
    FIELD
    -0.08
    datal
    -0.08
    åľ¨çĽ®
    -0.08
     Ingr
    -0.08
    å¹³çļĦ
    -0.07
    è°Ĭ
    -0.07
     аваÑĢ
    -0.07
    ÑĢид
    -0.07
    suite
    -0.07
    POSITIVE LOGITS
     constructed
    0.07
    icules
    0.07
    blocks
    0.07
     Uploaded
    0.07
     recursively
    0.06
    ä¸įåİĮ
    0.06
     itch
    0.06
    çķĻä¸ĭæĿ¥çļĦ
    0.06
    rovers
    0.06
    retch
    0.06
    Activations Density 0.003%

    No Known Activations