© 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. 45608
    Prev
    Next
    INDEX
    Explanations

    code examples and structure

    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
    ä¸ĢæĦı
    -0.07
    .remaining
    -0.07
    è·»
    -0.06
    ETR
    -0.06
    ä¸Ńæĸ°ç½ij
    -0.06
    лез
    -0.06
    转载请注æĺİ
    -0.06
     unlikely
    -0.06
    åıijæĶ¾
    -0.06
    inet
    -0.06
    POSITIVE LOGITS
    mons
    0.08
    èIJ±
    0.07
    åİ
    0.07
    aped
    0.07
    uids
    0.07
    æī®
    0.07
    æ¶Ł
    0.07
     espet
    0.07
    abeth
    0.07
    quette
    0.07
    Activations Density 0.001%

    No Known Activations