© 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. 4295
    Prev
    Next
    INDEX
    Explanations

    positive, neutral, dispute

    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
    ÛĮشاÙĨ
    -0.10
    çĦ¶å¤§
    -0.10
    imun
    -0.09
     freig
    -0.09
    ilah
    -0.09
    æĽ´æĸ°æĹ¥æľŁ
    -0.09
    irken
    -0.09
    stroy
    -0.09
    à¥Ĥप
    -0.09
    æľīéģĵ
    -0.08
    POSITIVE LOGITS
     means
    0.07
    è¿ĻæĦıåij³çĿĢ
    0.06
    ä¹Łå°±æĺ¯è¯´
    0.06
    ...
    0.06
    *
    0.06
     adm
    0.06
    ä¸Ķ
    0.06
    ä¸Ķä¸į
    0.06
    0.06
     berarti
    0.06
    Activations Density 0.279%

    No Known Activations