© 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. 62479
    Prev
    Next
    INDEX
    Explanations

    0 degrees

    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
    intas
    -0.09
    ingan
    -0.07
    ç¡®å®ļæĢ§
    -0.07
    inds
    -0.06
    ãģĹãģĭ
    -0.06
    åĽŀçŃĶéĩı
    -0.06
    fmt
    -0.06
    iaz
    -0.06
    odes
    -0.06
    ires
    -0.06
    POSITIVE LOGITS
    ä¸Ģ鸣
    0.08
    ish
    0.08
    à¸Ĥà¹īà¸Ń
    0.07
    czyn
    0.07
    elta
    0.07
    ä¸ĢæĪ·
    0.07
     kidding
    0.07
    egin
    0.07
    illante
    0.06
    uhan
    0.06
    Activations Density 0.022%

    No Known Activations