© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16956
    Prev
    Next
    INDEX
    Explanations

    historical dates and numbers

    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
    ister
    -0.07
    ,
    -0.06
     dar
    -0.06
    åħľ
    -0.06
    éļĶ
    -0.05
    jan
    -0.05
    æĿŁ
    -0.05
    /
    -0.05
     and
    -0.05
     greve
    -0.05
    POSITIVE LOGITS
    elper
    0.09
    uver
    0.08
    ä¸Ģæł·çļĦ
    0.08
    uvad
    0.08
    osti
    0.08
    resti
    0.08
    ä¸ĭä¸Ģç¯ĩ
    0.08
    nesc
    0.08
     reim
    0.07
    ossal
    0.07
    Activations Density 0.052%

    No Known Activations