© 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. 15897
    Prev
    Next
    INDEX
    Explanations

    orthogonal idempotents

    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
    éľĢè¦ģåIJĮ
    -0.08
     sofist
    -0.07
    адÑĮ
    -0.07
    ظة
    -0.07
     аз
    -0.07
    agrams
    -0.07
    _CID
    -0.07
    uong
    -0.07
    ìĬ¬
    -0.07
    Ỽ
    -0.07
    POSITIVE LOGITS
     repeated
    0.08
    çī¹æĢ§
    0.08
     ë°ĺë³µ
    0.07
     properties
    0.07
    çļĦæĢ§è´¨
    0.07
    efe
    0.07
     repet
    0.07
    othing
    0.07
    åıįå¤į
    0.07
    ç¹°ãĤĬè¿Ķ
    0.07
    Activations Density 0.007%

    No Known Activations