© 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. 13913
    Prev
    Next
    INDEX
    Explanations

    2 +

    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
     exemp
    -0.09
    fs
    -0.09
    edly
    -0.09
    anee
    -0.09
    管çIJĨåѦéĻ¢
    -0.08
    leos
    -0.08
    èµĦæł¼è¯ģ
    -0.08
    ä½Ľåħ°
    -0.08
    ceg
    -0.08
    eia
    -0.08
    POSITIVE LOGITS
     del
    0.06
    0.06
    read
    0.06
    åıĮèĥŀèĥİ
    0.06
    azing
    0.06
    é»İæĺİ
    0.06
    ancock
    0.05
    æľŁ
    0.05
     ving
    0.05
    æIJŃæ¡£
    0.05
    Activations Density 0.016%

    No Known Activations