© 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. 19183
    Prev
    Next
    INDEX
    Explanations

    tokens after punctuation

    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
    é¦ĸåħĪè¦ģ
    -0.08
    è°ĥ
    -0.08
    anon
    -0.08
    PTS
    -0.08
    ç»´å¥ĩ
    -0.07
    REDIS
    -0.07
    exual
    -0.07
     retten
    -0.07
     ÐłÐµÑĩÑĮ
    -0.07
    redi
    -0.07
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½
    0.07
    _relations
    0.07
    ItemId
    0.07
    èĢĮçŁ¥
    0.06
    æĢ»èµĦ产
    0.06
    å¿ĥæĤ¦
    0.06
    uiten
    0.06
     finally
    0.06
     relations
    0.06
    ró
    0.06
    Activations Density 0.021%

    No Known Activations