© 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. 26790
    Prev
    Next
    INDEX
    Explanations

    symmetric and metrical

    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
    awas
    -0.07
    anel
    -0.07
    तर
    -0.07
    ãĤ¿ãĥĥãĥģ
    -0.07
    éĢļè¿ĩä¸İ
    -0.07
    ÙĪائ
    -0.07
     pokok
    -0.07
    bes
    -0.07
    INGS
    -0.07
    _constants
    -0.07
    POSITIVE LOGITS
    对称
    0.14
     symmetric
    0.12
     Sym
    0.11
    sym
    0.11
     sym
    0.11
    Sym
    0.10
    ally
    0.09
    metrical
    0.09
     symmetry
    0.09
    -leaning
    0.09
    Activations Density 0.010%

    No Known Activations