© 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. 15400
    Prev
    Next
    INDEX
    Explanations

    gradual or slow progression

    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
     briefly
    -0.09
    å±ħé«ĺ
    -0.08
     pooled
    -0.07
    ạnh
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    etzen
    -0.07
    Brief
    -0.07
    brief
    -0.07
    ä¸ĢéĢļ
    -0.07
    ä¸ļåĬ¡æ°´å¹³
    -0.07
    POSITIVE LOGITS
     gradual
    0.22
    æ¸IJè¿Ľ
    0.21
    ç¼ĵæħ¢
    0.20
    æħ¢æħ¢
    0.19
    循åºıæ¸IJè¿Ľ
    0.18
    éĢIJæŃ¥
    0.17
    slow
    0.17
     gradually
    0.17
     slowly
    0.17
     slow
    0.16
    Activations Density 0.114%

    No Known Activations