© 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. 32755
    Prev
    Next
    INDEX
    Explanations

    lists data or content

    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
    et
    -0.06
    Âł
    -0.06
    ova
    -0.06
    (([
    -0.06
    è·¯éĢı
    -0.06
    oo
    -0.06
    çļ®åħ·
    -0.05
    ([{
    -0.05
    5
    -0.05
    é«ĺåİŁ
    -0.05
    POSITIVE LOGITS
    ä»»ä½ķåħ¶ä»ĸ
    0.09
     seterusnya
    0.09
    éĶ¦æ¶Ľ
    0.08
    æķ´ä¸ª
    0.08
    被åħ³éĹŃ
    0.08
    ä¸İä¹ĭ
    0.08
    æķ´ä¸ªéĹ®é¢ĺ
    0.08
    hots
    0.08
    ìĦľê´Ģ
    0.08
    è¿Ļæĺ¯ä¸ª
    0.08
    Activations Density 0.032%

    No Known Activations