© 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. 13925
    Prev
    Next
    INDEX
    Explanations

    script tags and column names

    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
    ofer
    -0.08
    olet
    -0.08
     ÑģоÑģÑĤ
    -0.08
    çĿ«
    -0.08
    tring
    -0.08
    holt
    -0.07
    iato
    -0.07
    éĻIJãĤĬ
    -0.07
    iou
    -0.07
    Ãłi
    -0.07
    POSITIVE LOGITS
    åĽĽçº§
    0.08
    æ¸ħçIJĨå¹²åĩĢ
    0.07
     cleaned
    0.07
    éĺ¶æ¢¯
    0.07
    濯
    0.07
    å¤ļå±Ĥ次
    0.07
    anson
    0.07
    _clean
    0.07
    orks
    0.06
    åİŁåĪĽæĸĩç«ł
    0.06
    Activations Density 0.001%

    No Known Activations