© 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. 17669
    Prev
    Next
    INDEX
    Explanations

    string, Ad, localized

    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
     Aviation
    -0.08
     aviation
    -0.07
    æ±°
    -0.06
    hled
    -0.06
    ä¸Ńæŀ¢
    -0.06
    ë¦ĩ
    -0.06
     ANSI
    -0.06
     merit
    -0.06
     habitual
    -0.06
    èĹ»
    -0.06
    POSITIVE LOGITS
    讲ä¹ī
    0.08
    å«ģ
    0.08
    localized
    0.08
    ectos
    0.08
    éľ¹éĽ³
    0.08
    ç»ı纪åħ¬åı¸
    0.08
     configurations
    0.08
    å¨ģ士
    0.08
    ħ
    0.07
    ariant
    0.07
    Activations Density 0.004%

    No Known Activations