© 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. 43414
    Prev
    Next
    INDEX
    Explanations

    special programming contexts

    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
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    prof
    -0.07
    汪æ´ĭ
    -0.07
    ÑĨе
    -0.07
    轨
    -0.07
    erring
    -0.06
    æ»´
    -0.06
    åĨħ容ç®Ģä»ĭ
    -0.06
     complimentary
    -0.06
     stead
    -0.06
    POSITIVE LOGITS
    pell
    0.07
    azos
    0.07
    æĭŃ缮
    0.07
    åħ°è¾¾
    0.07
    ÙĦز
    0.06
    .subplot
    0.06
    æĺ¯ç¬¬ä¸Ģ
    0.06
    uss
    0.06
    ONENT
    0.06
    noinspection
    0.06
    Activations Density 0.266%

    No Known Activations