© 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. 19907
    Prev
    Next
    INDEX
    Explanations

    first occurrence or followed

    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
    warts
    -0.07
    äºĨä¸Ģä¸ĭ
    -0.07
    ä¸įåĪĨ
    -0.06
     mera
    -0.06
    uler
    -0.06
    ä¸Ģä¸ĭ
    -0.06
    frames
    -0.06
    attend
    -0.06
    ثة
    -0.06
    wart
    -0.06
    POSITIVE LOGITS
    éĻĨç»Ń
    0.20
    缸继
    0.18
    éĻ¸çºĮ
    0.16
     progressively
    0.15
    åħĪåIJİ
    0.15
    éĢIJæŃ¥
    0.14
     sequentially
    0.14
    æľĢåħĪ
    0.14
     gradually
    0.13
    éĢIJä¸Ģ
    0.13
    Activations Density 0.248%

    No Known Activations