© 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. 64429
    Prev
    Next
    INDEX
    Explanations

    replaced or upgrade

    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
    ä¸įæĶ¾
    -0.08
    åĩıåħį
    -0.08
    agli
    -0.08
    edale
    -0.07
    andalone
    -0.07
    ettor
    -0.07
    eam
    -0.07
    æĤ£
    -0.07
     omitted
    -0.07
    .opensource
    -0.07
    POSITIVE LOGITS
    æĽ´æį¢
    0.22
    æį¢
    0.21
    æĽ¿æį¢
    0.20
    æį¢äºĨ
    0.19
    æį¢ä¸Ģ个
    0.18
    æĽ´æıĽ
    0.18
    æį¢ä¸ª
    0.17
    æıĽ
    0.17
    æį¢æĸ°
    0.17
    æį¢ä»£
    0.16
    Activations Density 0.529%

    No Known Activations