© 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. 42863
    Prev
    Next
    INDEX
    Explanations

    legal citations and file paths

    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
    è£ķ
    -0.07
    hed
    -0.06
    dddd
    -0.06
    룬
    -0.06
    .www
    -0.06
    Âł
    -0.06
    dress
    -0.06
    è°ģçŁ¥éģĵ
    -0.06
    åĩĭ
    -0.06
    æĽ´æľī
    -0.06
    POSITIVE LOGITS
    ensible
    0.08
    egi
    0.08
    emer
    0.08
    åı«å¥½
    0.08
     wikit
    0.07
    riz
    0.07
    äºİè¡Į
    0.07
    éĩijåŁİ
    0.07
    ecu
    0.07
    é²²é¹ı
    0.07
    Activations Density 0.010%

    No Known Activations