© 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. 2952
    Prev
    Next
    INDEX
    Explanations

    isometry, coordinate transformation, preserved structure

    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
    plin
    -0.08
    ä¸Ń空
    -0.08
    å¤ļ空
    -0.07
    åı¯çĶ¨çļĦ
    -0.07
     Redemption
    -0.07
    ä¸įä½ľä¸º
    -0.07
    à¦
    -0.07
    è¦ģéĹ»
    -0.07
    inson
    -0.06
    hurst
    -0.06
    POSITIVE LOGITS
     preserving
    0.09
     preserve
    0.08
     preserv
    0.08
     preservation
    0.08
     preserved
    0.08
     preserves
    0.08
    preserve
    0.08
     Eu
    0.08
    è·Ŀ离
    0.08
    uver
    0.08
    Activations Density 0.003%

    No Known Activations