© 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. 18932
    Prev
    Next
    INDEX
    Explanations

    image pyramid and zoom

    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
     Cowboy
    -0.08
    é¢ģ
    -0.07
    æķ¢
    -0.07
    meld
    -0.07
     Slate
    -0.07
     lean
    -0.07
    rost
    -0.07
    ä½ľä¸ºä¸Ģ个
    -0.07
     Sadd
    -0.06
    åĢ¾
    -0.06
    POSITIVE LOGITS
    缩æĶ¾
    0.10
    zoom
    0.09
     zoom
    0.09
    缩å°ı
    0.09
    è²ī
    0.09
     маÑģÑĪÑĤа
    0.09
     recursively
    0.09
     hierarchical
    0.09
    缩
    0.08
     scaling
    0.08
    Activations Density 0.021%

    No Known Activations