© 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. 42248
    Prev
    Next
    INDEX
    Explanations

    legal and financial contexts

    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
     iepazÄ«Å¡anÄģs
    -0.08
    迪奥
    -0.08
    å®īè¾¾
    -0.08
     -$
    -0.07
    atap
    -0.07
    ->$
    -0.07
    -ng
    -0.07
    umon
    -0.07
    转载请注æĺİ
    -0.07
    ï¸İ
    -0.07
    POSITIVE LOGITS
    æĺ¯æĮĩåľ¨
    0.09
    æĺ¯æĮĩ
    0.08
     literal
    0.08
    æĮĩçļĦ
    0.08
     Literal
    0.08
    ä¸įåĮħæĭ¬
    0.08
    å¿ħé¡»æĺ¯
    0.07
     literally
    0.07
    æĮĩçļĦæĺ¯
    0.07
    æĮĩ
    0.07
    Activations Density 0.035%

    No Known Activations