© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14015
    Prev
    Next
    INDEX
    Explanations

    symmetric, asymmetric, sym, antis

    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
    ä½³èĬĤ
    -0.08
    ä¸įè¦ģéĶĻè¿ĩ
    -0.07
     dormant
    -0.07
    sov
    -0.07
    ufe
    -0.07
    游离
    -0.07
    ouz
    -0.07
    éĿĴæĿ¾
    -0.07
    è¾Ħ
    -0.07
    人æĦı
    -0.07
    POSITIVE LOGITS
     symmetric
    0.10
     asym
    0.08
    åģ¶
    0.08
     asymmetric
    0.08
    oyer
    0.08
    ä¸į对称
    0.08
    Sym
    0.08
    对称
    0.08
     antis
    0.08
     sym
    0.08
    Activations Density 0.009%

    No Known Activations