© 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. 17450
    Prev
    Next
    INDEX
    Explanations

    optical transitions

    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
     Äijá»±ng
    -0.07
    Ïģιά
    -0.06
    壬
    -0.06
     Burr
    -0.06
    isé
    -0.06
    urator
    -0.06
    ise
    -0.06
    åŃĺæĶ¾
    -0.06
    屯
    -0.06
    izado
    -0.06
    POSITIVE LOGITS
    åıijçĶŁæŶ
    0.09
    åıijçĶŁåľ¨
    0.09
    Forbidden
    0.09
    chsel
    0.09
    è·¨è¶Ĭ
    0.08
     forbidden
    0.08
    è¿ģ
    0.08
    kena
    0.08
    icket
    0.08
     involving
    0.08
    Activations Density 0.006%

    No Known Activations