© 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. 40845
    Prev
    Next
    INDEX
    Explanations

    scale and size

    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
    æ¸Ĭ
    -0.07
    å¿ħ须符åIJĪ
    -0.07
    iw
    -0.07
    çİ°æľī
    -0.06
    æĹłåıĮ
    -0.06
    fir
    -0.06
    åıĶ
    -0.06
    æľīçļĦ人
    -0.06
    çİ°æľīçļĦ
    -0.06
    ivor
    -0.06
    POSITIVE LOGITS
    Domin
    0.08
    èĩ³å°ijè¦ģ
    0.07
    -scale
    0.07
    çľĭä¸įæ¸ħ
    0.07
    åķĨåľĪ
    0.07
    forge
    0.07
    ä¸»å¯¼åľ°ä½į
    0.07
    estad
    0.07
    /modal
    0.07
     ratio
    0.07
    Activations Density 0.005%

    No Known Activations