© 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. 24812
    Prev
    Next
    INDEX
    Explanations

    finding patterns and relationships

    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
    æݪ置
    -0.07
     woes
    -0.07
    áĥĹ
    -0.07
    onga
    -0.07
    æ¯ıä¸ĢæŃ¥
    -0.07
    asuring
    -0.07
    ODA
    -0.06
    ĵĺ
    -0.06
     dạ
    -0.06
    ialis
    -0.06
    POSITIVE LOGITS
     patterns
    0.20
     Patterns
    0.17
    patterns
    0.16
    è§Ħå¾ĭ
    0.16
     pattern
    0.15
    Patterns
    0.14
    -pattern
    0.14
     Pattern
    0.14
    (pattern
    0.14
    Pattern
    0.13
    Activations Density 0.090%

    No Known Activations