© 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. 22017
    Prev
    Next
    INDEX
    Explanations

    If you

    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
    praw
    -0.07
    valuate
    -0.06
    çĤ¹æĴŃ
    -0.06
    æľ¬æĸĩ为
    -0.06
     Fisc
    -0.06
    ÏĦαι
    -0.06
    è¿Ļéĥ½æĺ¯
    -0.06
     pro
    -0.06
    åħĪåľ¨
    -0.06
    krét
    -0.06
    POSITIVE LOGITS
    éľĢè¦ģ使çĶ¨
    0.09
    ä¸įåIJĮæĦı
    0.09
    æľīä»»ä½ķ
    0.08
    纳æĸ¯
    0.08
    å¦ĤæŀľéľĢè¦ģ
    0.07
    æľīä»»ä½ķçĸijéĹ®
    0.07
    åĽłæѤèĢĮ
    0.07
    åıijçİ°éĹ®é¢ĺ
    0.07
    å®ŀåľ¨
    0.07
    å®ŀåľ¨æĺ¯
    0.07
    Activations Density 0.123%

    No Known Activations