© 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. 32859
    Prev
    Next
    INDEX
    Explanations

    similarity comparisons

    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
    æĪĸèĢħ缴æİ¥
    -0.06
    orama
    -0.06
    serter
    -0.06
    çĶµåŃIJåķĨåĬ¡æľīéĻIJåħ¬åı¸
    -0.06
    esser
    -0.06
    åĴĨ
    -0.06
     Tanger
    -0.06
    åı¯èĥ½çļĦ
    -0.06
    vera
    -0.06
     Consortium
    -0.06
    POSITIVE LOGITS
    类似çļĦ
    0.16
     similar
    0.14
    类似
    0.13
     similarly
    0.13
    similar
    0.13
    类似äºİ
    0.13
    çĽ¸ä¼¼çļĦ
    0.13
     Similar
    0.13
     ähnliche
    0.13
    Similar
    0.13
    Activations Density 0.184%

    No Known Activations