© 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. 38915
    Prev
    Next
    INDEX
    Explanations

    orthogonal reflection, projection, preservation

    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
     trầm
    -0.08
    toon
    -0.07
    mlin
    -0.07
    минÑĥ
    -0.07
    wan
    -0.07
    atorium
    -0.07
    tings
    -0.07
    ä¸įå¦Ĥ
    -0.07
    outed
    -0.07
    ichten
    -0.07
    POSITIVE LOGITS
    preserve
    0.09
    ä¿ĿåĢ¼
    0.09
     preservation
    0.09
     preserving
    0.08
    _pres
    0.08
     Preservation
    0.08
     preserves
    0.07
     preserve
    0.07
    æ³
    0.07
    ä¹ĭ士
    0.07
    Activations Density 0.008%

    No Known Activations