© 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. 18697
    Prev
    Next
    INDEX
    Explanations

    social media posts and hashtags

    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
    Visitor
    -0.07
     Guest
    -0.07
    à¹ĥà¸Ļà¹Ģวà¹ĩà¸ļà¹Ħà¸ĭà¸ķà¹Į
    -0.07
    DVD
    -0.07
    æ¡Į
    -0.06
     DVD
    -0.06
    åĿĩæĿ¥èĩªäºĴèģĶç½ij
    -0.06
    å½ķéŁ³
    -0.06
    çĶµåŃIJéĤ®ä»¶
    -0.06
    ç½ij游å°ı说
    -0.06
    POSITIVE LOGITS
     hashtag
    0.13
     hashtags
    0.11
    htag
    0.11
     (@
    0.10
    htags
    0.09
    转åıij
    0.09
     @
    0.09
     #
    0.09
     **#
    0.08
     repost
    0.08
    Activations Density 0.204%

    No Known Activations