© 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. 12515
    Prev
    Next
    INDEX
    Explanations

    Hardy’s, positive definite, curvature

    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
    caras
    -0.08
    åIJĦåı¸
    -0.08
    aldas
    -0.08
    Asc
    -0.07
     complexities
    -0.07
    ezas
    -0.07
    abox
    -0.07
     unarmed
    -0.07
    ciso
    -0.07
     nrows
    -0.07
    POSITIVE LOGITS
     portion
    0.08
    ersistent
    0.07
    åĽºå®ļ
    0.07
    etta
    0.07
    èĻ½å°ı
    0.07
    èŃ²
    0.07
    æģĴ
    0.07
    åĪĨ许
    0.07
    åĽºå®ļçļĦ
    0.07
    portion
    0.06
    Activations Density 0.008%

    No Known Activations