© 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. 61652
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and spatial positions

    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
    azzi
    -0.06
    åľ¨æ°´éĩĮ
    -0.06
    ÑĢони
    -0.06
    lew
    -0.06
    èµ°åľ¨
    -0.06
    e
    -0.06
     continuity
    -0.06
    heit
    -0.06
    r
    -0.06
    ilan
    -0.06
    POSITIVE LOGITS
    à¹ģหà¹Īà¸ĩà¸Ļีà¹ī
    0.09
    å¤Ħ女
    0.09
    éĢĶä¸Ń
    0.09
     angekommen
    0.09
    ä¸Ģè¶Ł
    0.09
    ampa
    0.09
     tujuan
    0.09
    åĿĢ
    0.08
    éĻĦè¿ijçļĦ
    0.08
    Ä«b
    0.08
    Activations Density 0.019%

    No Known Activations