© 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. 25667
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by specific words or non-latin characters

    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
    ÄĽnÃŃ
    -0.10
    åı£æ°Ķ
    -0.09
    åĨį以
    -0.08
    ãĥ¼ãĤ¯
    -0.08
    ieb
    -0.07
     vela
    -0.07
    åĨįéĢļè¿ĩ
    -0.07
    ölker
    -0.07
    ุ
    -0.07
    rasz
    -0.07
    POSITIVE LOGITS
    æĻĹ
    0.08
    æī§è¡Įç¨ĭåºı
    0.07
    é¦ĸåħĪéľĢè¦ģ
    0.07
    atik
    0.06
    éľĢè¦ģè¿Ľè¡Į
    0.06
    é¦ĸåħĪ
    0.06
     abon
    0.06
    reeting
    0.06
    æĮīçħ§è§Ħå®ļ
    0.06
    æĹłåIJį
    0.06
    Activations Density 0.007%

    No Known Activations