© 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. 32337
    Prev
    Next
    INDEX
    Explanations

    mathematical notation symbols

    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
    Âł
    -0.07
    pit
    -0.06
    odle
    -0.06
    endus
    -0.06
    óp
    -0.06
    åĶIJ
    -0.06
    ansir
    -0.06
    ENCES
    -0.06
    ëĭ¹
    -0.06
    adou
    -0.06
    POSITIVE LOGITS
    å®ĥæĺ¯ä¸Ģ个
    0.08
     ervan
    0.07
    ä¸İä¹ĭ
    0.07
    ÙĬص
    0.07
    项
    0.07
    èĢħåı¯
    0.07
    øv
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.07
     bukanlah
    0.07
    ç»Ļå®ĥ
    0.07
    Activations Density 0.004%

    No Known Activations