© 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. 38972
    Prev
    Next
    INDEX
    Explanations

    only

    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
    两çĶ¨
    -0.08
     kew
    -0.07
    adamente
    -0.07
    idon
    -0.07
    æ¯ıä¸Ģ天
    -0.07
    ?f
    -0.07
    evity
    -0.07
    èĻ½çĦ¶æ²¡æľī
    -0.07
    always
    -0.07
    赫å°Ķ
    -0.07
    POSITIVE LOGITS
    åı¯è¨Ģ
    0.11
     imaginable
    0.10
    åģļçļĦå°±æĺ¯
    0.10
     conceivable
    0.10
     whatsoever
    0.09
     ever
    0.09
     besides
    0.09
    èİ«è¿ĩäºİ
    0.09
     EVER
    0.09
     überhaupt
    0.09
    Activations Density 0.049%

    No Known Activations