© 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. 8008
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, LaTeX symbols

    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
    ÙĨÙĪÙĨ
    -0.08
     outr
    -0.07
    éħį
    -0.07
    åĨĻä¸Ģç¯ĩ
    -0.06
    ogr
    -0.06
    &w
    -0.06
    åı°ä¸ĬçļĦ
    -0.06
     HI
    -0.06
    æįİ
    -0.06
    çļ®çļĦ
    -0.06
    POSITIVE LOGITS
    abo
    0.09
    æŶä¸ĭ
    0.09
    ekat
    0.08
    æľĪåı·
    0.08
    éĺģä¸ĭ
    0.08
    ثة
    0.08
    Tec
    0.08
    боÑĩ
    0.08
     Indi
    0.08
    模èĮĥ
    0.07
    Activations Density 0.009%

    No Known Activations