© 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. 14696
    Prev
    Next
    INDEX
    Explanations

    javascript code artifacts

    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
    configs
    -0.07
    _customize
    -0.07
    abilit
    -0.07
    .cf
    -0.06
    ä¸įåŃķ
    -0.06
    avior
    -0.06
    两åı£
    -0.06
    onis
    -0.06
    ordi
    -0.06
    iland
    -0.06
    POSITIVE LOGITS
    æĸ°çĶŁ
    0.07
    ijt
    0.07
    åĢ¾åŁİ
    0.07
    /commons
    0.07
    ÙĨب
    0.07
     showdown
    0.07
    _NATIVE
    0.07
    æĢĢ
    0.07
     ubiquitous
    0.06
    -clean
    0.06
    Activations Density 0.020%

    No Known Activations