© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13962
    Prev
    Next
    INDEX
    Explanations

    additional information or joining

    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
    ivia
    -0.07
    imar
    -0.06
    onda
    -0.06
    imers
    -0.06
    imer
    -0.06
    以å°ı
    -0.06
    림
    -0.06
    çĽ¸å¯¹åºĶçļĦ
    -0.06
    opp
    -0.06
    lexer
    -0.06
    POSITIVE LOGITS
     additional
    0.21
    é¢Ŀå¤ĸçļĦ
    0.19
    é¢Ŀå¤ĸ
    0.19
    additional
    0.18
    Additional
    0.17
     additionally
    0.17
     thêm
    0.16
     adicionales
    0.16
     supplémentaire
    0.16
     Additional
    0.16
    Activations Density 0.270%

    No Known Activations