© 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. 50005
    Prev
    Next
    INDEX
    Explanations

    European, poly, novel, forgiveness

    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
    imos
    -0.07
    个好
    -0.07
    以身
    -0.07
    :index
    -0.07
    à¸Ĺีà¹Īà¸Īะ
    -0.06
    åĵªäºĽ
    -0.06
    åŃIJäºĨ
    -0.06
    çĶ¨ä»¥
    -0.06
    `.
    -0.06
    æķ°ä»¥
    -0.06
    POSITIVE LOGITS
    èijĹ称
    0.14
    为åīįæıIJ
    0.13
    为ä¾ĭ
    0.13
    为å¥ijæľº
    0.13
    çļĦæĸ¹å¼ıè¿Ľè¡Į
    0.13
    ä¸ºåŁºç¡Ģ
    0.12
    æĸ¹å¼ıè¿Ľè¡Į
    0.12
    åijĬç»Ī
    0.12
    çļĦåIJįä¹ī
    0.11
    为æĬĵæīĭ
    0.11
    Activations Density 0.018%

    No Known Activations