© 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. 41572
    Prev
    Next
    INDEX
    Explanations

    central axis and symmetry

    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
    è¿Ľè¡Įè¯Ħä¼°
    -0.08
    åŃĺéĩı
    -0.08
    oven
    -0.08
    ç»ĵä¼´
    -0.08
    å½¢èī²
    -0.08
    对人类
    -0.07
    fras
    -0.07
    icol
    -0.07
     Ingr
    -0.07
     Plage
    -0.07
    POSITIVE LOGITS
     symmetry
    0.13
    对称
    0.12
     symmetric
    0.11
    Sym
    0.10
     Sym
    0.09
    sym
    0.09
     sym
    0.09
     splitting
    0.08
     central
    0.08
    ä¸Ń央
    0.08
    Activations Density 0.001%

    No Known Activations