© 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. 4386
    Prev
    Next
    INDEX
    Explanations

    . and things

    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
    cion
    -0.09
    вок
    -0.08
    ãģĤãĤĮ
    -0.08
    meros
    -0.07
     alone
    -0.07
     baud
    -0.07
    .ci
    -0.07
    ciri
    -0.07
     abon
    -0.07
    cim
    -0.07
    POSITIVE LOGITS
    çļĦ综åIJĪ
    0.07
    å½¢æĪIJä¸Ģ个
    0.07
    活水
    0.07
    使æĪij
    0.07
    haft
    0.07
    éľĢè¦ģèĢĥèĻij
    0.07
    综åIJĪ
    0.06
    ä¸įç®Ģåįķ
    0.06
    å¤įæĿĤçļĦ
    0.06
    ner
    0.06
    Activations Density 0.014%

    No Known Activations