© 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. 47869
    Prev
    Next
    INDEX
    Explanations

    different aspects

    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
    Extras
    -0.08
    ÑĸÑĢ
    -0.08
    ড়া
    -0.07
    inne
    -0.07
     equ
    -0.07
    åºķçļĦ
    -0.07
    ÙĦÙĬÙħ
    -0.07
    èĢĥè¯ķæŶéĹ´
    -0.06
    ãģ¤ãģĦ
    -0.06
    ancis
    -0.06
    POSITIVE LOGITS
    æĺ¯æĢİæł·
    0.09
    æĺ¯å¦Ĥä½ķ
    0.09
    beh
    0.09
    åıĬåħ¶
    0.08
    åIJĦåħ·
    0.08
    éĤ£äºĽäºº
    0.08
    æ¼Ķåıĺ
    0.08
     ÙĪÙĥÙĬÙģ
    0.08
    æĺ¯æĢİä¹Ī
    0.08
    ä½ķ以
    0.08
    Activations Density 0.144%

    No Known Activations