© 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. 63273
    Prev
    Next
    INDEX
    Explanations

    names ending in 'el', 'ster', 'ingles', 'anth', 'B', 'li', 'Day', 'hem', 'ic', 'ley'

    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
    åľ¨ä¸ī
    -0.08
    dav
    -0.08
    åľ¨äº§åĵģ
    -0.07
    veloper
    -0.07
    witter
    -0.07
    _specs
    -0.07
    tmpl
    -0.07
    zyb
    -0.07
     Mixed
    -0.07
    IVE
    -0.07
    POSITIVE LOGITS
    ä¸İ
    0.08
     inherits
    0.07
     inherit
    0.07
    åĴĮæµ·
    0.07
    éĢĴè¡¥
    0.06
     counterpart
    0.06
    æ¯Ķ
    0.06
    _vs
    0.06
    çĽ¸å¯¹äºİ
    0.06
     internet
    0.06
    Activations Density 0.233%

    No Known Activations