© 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. 46560
    Prev
    Next
    INDEX
    Explanations

    file types identification

    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
    با
    -0.08
    ronic
    -0.08
    ecer
    -0.08
    è¦ģ对
    -0.07
    ets
    -0.07
    astre
    -0.07
    ãģ¦ãĤĭ
    -0.07
    iche
    -0.07
    izzle
    -0.07
    cript
    -0.07
    POSITIVE LOGITS
    èĩªå·±
    0.10
    etheless
    0.10
    èĩªå·±è¢«
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    нваÑĢ
    0.08
    èĩªå·±èº«ä¸Ĭ
    0.08
    gether
    0.08
    åĽ¾æĸ¯
    0.08
    efois
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    Activations Density 0.054%

    No Known Activations