© 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. 42570
    Prev
    Next
    INDEX
    Explanations

    code snippets and strings

    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
    -m
    -0.06
    å®Įåħ¨
    -0.06
    -0.06
     rooting
    -0.06
     aw
    -0.06
    3
    -0.06
     wh
    -0.05
    ä»ĭ
    -0.05
    ity
    -0.05
    ç½ijç«Ļåľ°åĽ¾
    -0.05
    POSITIVE LOGITS
     Pronto
    0.08
    ubr
    0.08
    à®Łà¯įà®ļ
    0.08
    æł¼éĩĮ
    0.08
    pected
    0.08
    obet
    0.08
    微信åı·
    0.08
    oland
    0.08
    ijing
    0.08
    adress
    0.08
    Activations Density 0.033%

    No Known Activations