© 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. 56610
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs

    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
     Ahead
    -0.07
    wod
    -0.07
    Inline
    -0.07
    椿
    -0.07
    éĢĤå®ľ
    -0.06
    è¡Į礼
    -0.06
    åºĶæīĭ
    -0.06
    pga
    -0.06
    ete
    -0.06
    uló
    -0.06
    POSITIVE LOGITS
    å¸Ń
    0.07
    çļĦä¸Ģçīĩ
    0.07
    ongs
    0.07
    udo
    0.07
     promised
    0.06
    好ä¸į容æĺĵ
    0.06
    ä¸įå°½
    0.06
    .vars
    0.06
    mitt
    0.06
    param
    0.06
    Activations Density 0.001%

    No Known Activations