© 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. 12806
    Prev
    Next
    INDEX
    Explanations

    vector related topics

    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
    adero
    -0.08
    Kamis
    -0.08
    æݥ触çļĦ
    -0.08
    garan
    -0.07
    没æľīæī¾åĪ°
    -0.07
    _patterns
    -0.07
    Patterns
    -0.07
    жеÑĢ
    -0.07
    è§ģå¾Ĺ
    -0.07
    пеÑĢа
    -0.07
    POSITIVE LOGITS
    çŁ¢éĩı
    0.10
     vector
    0.09
     directional
    0.09
     vectors
    0.08
     direction
    0.08
    æĸ¹ä½į
    0.08
    å¿ħ须注æĺİ
    0.08
     vec
    0.08
    .Direction
    0.08
     yön
    0.08
    Activations Density 0.005%

    No Known Activations