© 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. 48578
    Prev
    Next
    INDEX
    Explanations

    code related terms

    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
    éĻµ
    -0.07
    粧
    -0.06
    @if
    -0.06
    ä»İèĢĮ使
    -0.06
    ä¸½å¨ľ
    -0.06
    éķĤ
    -0.06
    å°¼åħĭ
    -0.06
    è¿ĻèĤ¡
    -0.06
    çķĶ
    -0.06
     pann
    -0.06
    POSITIVE LOGITS
    inel
    0.07
    _marshall
    0.07
    -worker
    0.07
    _FORE
    0.07
    zeÅĽ
    0.07
    λάβ
    0.07
    äºŃ
    0.07
    quee
    0.07
    åĥıä¸Ģåıª
    0.06
    ampion
    0.06
    Activations Density 0.013%

    No Known Activations