© 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. 43381
    Prev
    Next
    INDEX
    Explanations

    symmetry breaking, vacuum, field, organic

    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
    çĶ²çº§
    -0.07
    imson
    -0.07
    èī¯å¿ĥ
    -0.07
    rud
    -0.07
    vented
    -0.06
    zell
    -0.06
    æĸ°éĶIJ
    -0.06
     Bout
    -0.06
    bish
    -0.06
    æĸ°å®ī
    -0.06
    POSITIVE LOGITS
    稳
    0.08
    Contracts
    0.07
    dev
    0.07
     firme
    0.07
    空èĻļ
    0.07
    æĭīä¸Ŀ
    0.07
    éŀį
    0.07
    åĨ»
    0.07
    ä¸įéĢĢ
    0.07
    pher
    0.07
    Activations Density 0.002%

    No Known Activations