© 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. 64854
    Prev
    Next
    INDEX
    Explanations

    diagonalization, transform, matrices

    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
    apé
    -0.08
    è¡Ķ
    -0.08
    ÑĢави
    -0.08
    å°ģåı£
    -0.08
    regel
    -0.07
     inadvert
    -0.07
    å°ıèħ¹
    -0.07
    æݨç®Ĺ
    -0.07
    anoi
    -0.07
    utto
    -0.07
    POSITIVE LOGITS
     diagonal
    0.08
    éĺµ
    0.08
     orthogonal
    0.08
    lle
    0.07
    transform
    0.07
     Decom
    0.07
    æ±Ĺ
    0.07
    å½»åºķçļĦ
    0.07
     decom
    0.07
    ennon
    0.07
    Activations Density 0.008%

    No Known Activations