© 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. 30469
    Prev
    Next
    INDEX
    Explanations

    code keywords and syntax

    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
    DIR
    -0.08
    SID
    -0.08
    è¡Ģæµģ
    -0.07
    онаÑĤ
    -0.07
    天å®ī
    -0.07
    enton
    -0.07
    å°ĶèĴĻ
    -0.07
    ä¹łä½ľ
    -0.07
     Abbott
    -0.07
    iato
    -0.07
    POSITIVE LOGITS
    {return
    0.09
    为æŃ¢
    0.07
     returning
    0.07
     cáºŃn
    0.07
     recognised
    0.07
    uing
    0.07
    åģľæŃ¢
    0.07
     return
    0.07
    Returning
    0.07
    ä¹ĭæŶ
    0.07
    Activations Density 0.010%

    No Known Activations