© 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. 62791
    Prev
    Next
    INDEX
    Explanations

    financial data and limits

    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
    å¼Ģåı£è¯´éģĵ
    -0.07
    FAILURE
    -0.07
    åĽłä¸ºè¿Ļ
    -0.07
    cede
    -0.07
    гл
    -0.07
    DIFF
    -0.07
    &id
    -0.07
    è®
    -0.07
    RITE
    -0.07
    ovsky
    -0.07
    POSITIVE LOGITS
    ï¼Ī
    0.15
     (
    0.11
    ãĢıï¼Ī
    0.10
    ãĢįï¼Ī
    0.10
     ï¼Ī
    0.10
    (with
    0.10
    *(
    0.08
    æĮī
    0.08
    (
    0.08
    (in
    0.08
    Activations Density 0.514%

    No Known Activations