© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7197
    Prev
    Next
    INDEX
    Explanations

    fractals, sequences, 1-dimensional, maps, cycles, Rodriguez

    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
    Negative Logits
     wire
    -0.08
    çŁ¢
    -0.07
    Wire
    -0.07
     Geg
    -0.07
     Wire
    -0.07
    éŁ§å¸¦
    -0.07
    wire
    -0.07
    umen
    -0.06
    çĦĬæİ¥
    -0.06
    轻轻æĿ¾
    -0.06
    POSITIVE LOGITS
    ycles
    0.09
     cycles
    0.08
    _sequence
    0.08
     cycle
    0.08
    /Instruction
    0.08
     Cycle
    0.08
    jeta
    0.07
    åºıåĪĹ
    0.07
    onaut
    0.07
     sequence
    0.07
    Activations Density 0.014%

    No Known Activations