© 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. 4087
    Prev
    Next
    INDEX
    Explanations

    opening parentheses followed by code tokens

    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
    schuh
    -0.08
    stead
    -0.08
    ToFront
    -0.07
    ÑģнÑĥÑİ
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    ommen
    -0.07
    rud
    -0.07
    agung
    -0.07
    besar
    -0.07
    yh
    -0.07
    POSITIVE LOGITS
    	ext
    0.08
    ï¼Łï¼ī
    0.07
    ãģĦãĤıãĤĨãĤĭ
    0.07
    以ä¸ĭç®Ģ称
    0.07
    åīįæıIJæĺ¯
    0.07
    åį³
    0.07
    ł
    0.07
    >>)
    0.07
    æŃ¤ä¸º
    0.07
    åĮħéĤ®
    0.06
    Activations Density 0.013%

    No Known Activations