© 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. 43784
    Prev
    Next
    INDEX
    Explanations

    years since projects

    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
    æŁ¥å®ŀ
    -0.08
    Äı
    -0.07
    ä¸įèĢģ
    -0.06
    ident
    -0.06
    ãĥ³ãĤ¹
    -0.06
    èħĬ
    -0.06
    ĥĿ
    -0.06
    els
    -0.06
    åĽŀæī§
    -0.06
    åĨµ
    -0.06
    POSITIVE LOGITS
    toa
    0.09
    θÏį
    0.09
    à¹Ģà¸Ńà¸ģ
    0.09
    ICO
    0.08
    appa
    0.07
    å¢ħ
    0.07
    以å¤ĸ
    0.07
     Buffered
    0.07
    å¦Ĥä½ķéĢļè¿ĩ
    0.07
    CurrentValue
    0.07
    Activations Density 0.001%

    No Known Activations