© 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. 43365
    Prev
    Next
    INDEX
    Explanations

    Weyburn

    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
    åĢį
    -0.07
    èħ°å¸¦
    -0.07
    çĻ¾åĢį
    -0.07
    ä¸įæĭĶ
    -0.06
    باش
    -0.06
    çľ¼å¸ĺ
    -0.06
     Cain
    -0.06
    ä¼ł
    -0.06
    á»ĩu
    -0.05
    ever
    -0.05
    POSITIVE LOGITS
    ÑĢена
    0.09
    ÑĤон
    0.08
    lobber
    0.08
    nict
    0.08
    lds
    0.08
    ió
    0.08
    dle
    0.08
    dav
    0.08
    LOUR
    0.08
    hias
    0.08
    Activations Density 0.001%

    No Known Activations