© 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. 20123
    Prev
    Next
    INDEX
    Explanations

    programming task context

    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
    Ùħد
    -0.08
    æħµ
    -0.08
     Prem
    -0.07
     prezi
    -0.07
    å¹´æ¯ķä¸ļäºİ
    -0.07
    λεγ
    -0.07
     subur
    -0.07
     ump
    -0.07
    odz
    -0.07
    çļĦä¸Ģåijĺ
    -0.06
    POSITIVE LOGITS
    ç´§æİ¥çĿĢ
    0.10
    åIJİç»Ń
    0.09
    à¸ķà¹Ī
    0.08
    éĢĴ
    0.08
    oui
    0.08
    imat
    0.07
    çĭ¬ç«ĭ
    0.07
    æ±Ĥ
    0.07
    缸åħ³èģĶ
    0.07
    .related
    0.07
    Activations Density 0.017%

    No Known Activations