© 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. 57255
    Prev
    Next
    INDEX
    Explanations

    mentally, in head, laboratory

    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
    翼
    -0.07
    bund
    -0.07
    åī¯
    -0.07
    éŁŃ
    -0.07
    åĵĦ
    -0.06
    hoff
    -0.06
    æĶ
    -0.06
    åĽ
    -0.06
    çŀĴ
    -0.06
    roud
    -0.06
    POSITIVE LOGITS
    ãģ£ãģĵ
    0.08
    kira
    0.08
    irst
    0.08
    eldon
    0.08
    sache
    0.08
    ëŁŃ
    0.08
    cona
    0.07
    oola
    0.07
    olec
    0.07
    ãĤ¯ãĥŃãĤ¹
    0.07
    Activations Density 0.002%

    No Known Activations