© 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. 40080
    Prev
    Next
    INDEX
    Explanations

    published, Singapore, charts, create, Technology, Bash, to, two, 2, drums

    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
    åķ¡
    -0.08
    uen
    -0.08
    ipas
    -0.07
    моÑĤ
    -0.07
    িনি
    -0.07
    APON
    -0.07
     afer
    -0.07
    æ¶Ĥä¸Ĭ
    -0.07
    OnChange
    -0.07
    ÑĪе
    -0.07
    POSITIVE LOGITS
    代ä¹ĭ
    0.08
    æ£ł
    0.07
    ä¸İæĪij们èģĶç³»
    0.07
    yle
    0.07
    å¼
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.06
    ä¸ĭåIJĮ
    0.06
     Edi
    0.06
    è´¤
    0.06
     Trophy
    0.06
    Activations Density 0.231%

    No Known Activations