© 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. 49051
    Prev
    Next
    INDEX
    Explanations

    technically, strictly, sense

    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
    erber
    -0.09
     readily
    -0.08
    ап
    -0.08
    ÏģÏĮ
    -0.08
    æĥ³å¿ħ
    -0.08
    èĩªçĦ¶èĢĮçĦ¶
    -0.08
    è½»èĢĮæĺĵ举
    -0.08
    Unchecked
    -0.08
    ãĥ¼ãĤ¹
    -0.08
    аве
    -0.07
    POSITIVE LOGITS
    åľ°è¯´
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.07
    ä¸įç®Ĺ
    0.07
     sih
    0.07
    ç¼Ģ
    0.07
    Ùĭ
    0.07
    ä¸į离
    0.06
    mark
    0.06
    embl
    0.06
     shouldn
    0.06
    Activations Density 0.016%

    No Known Activations