© 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. 21848
    Prev
    Next
    INDEX
    Explanations

    years

    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
    owe
    -0.07
    empt
    -0.06
    è¿Ľ
    -0.06
     emb
    -0.06
    å¿«å¿«ä¹IJ
    -0.06
    uns
    -0.06
     Tribal
    -0.06
     Emb
    -0.06
    erc
    -0.06
    åĩĨå¤ĩ好äºĨåIJĹ
    -0.06
    POSITIVE LOGITS
    æĹ¥æŃ¢
    0.09
    .infinity
    0.08
    olim
    0.08
    为æŃ¢
    0.08
    ä¸įéĻIJ
    0.08
     inclusive
    0.08
    /rfc
    0.07
    gota
    0.07
    éĻIJä»·
    0.07
     kautta
    0.07
    Activations Density 0.044%

    No Known Activations