© 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. 7402
    Prev
    Next
    INDEX
    Explanations

    ordered phases and symmetry breaking

    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
    ç½ijåıĭçļĦ
    -0.07
     spare
    -0.07
    ä¸įæĦ§
    -0.06
    PLIED
    -0.06
    é»ĥéĩij
    -0.06
    å±ħæĺĵ
    -0.06
    ä½¼
    -0.06
     sped
    -0.06
    è¯ģåĪ¸èĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.06
    geom
    -0.06
    POSITIVE LOGITS
    稳
    0.09
    èĩªåıij
    0.09
    对称
    0.08
    otty
    0.08
     formally
    0.08
    CRY
    0.08
    åĪ¤
    0.08
    utow
    0.07
    .mean
    0.07
    anh
    0.07
    Activations Density 0.017%

    No Known Activations