© 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. 49932
    Prev
    Next
    INDEX
    Explanations

    tasks and research assignments

    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
    ç¡®å®ŀ
    -0.07
    缸åıį
    -0.07
    ç¡®å®ŀæĺ¯
    -0.06
    ey
    -0.06
    ear
    -0.06
    achel
    -0.06
     dziaÅĤa
    -0.06
    atte
    -0.06
    ajan
    -0.06
    eref
    -0.06
    POSITIVE LOGITS
    è¦ģæ±Ĥåľ¨
    0.11
    åħ·ä½ĵè¦ģæ±Ĥ
    0.11
     tasks
    0.10
    çļĦä»»åĬ¡
    0.09
     Tasks
    0.09
    è¿ĻäºĽéĹ®é¢ĺ
    0.09
    /tasks
    0.09
    Tasks
    0.09
    tasks
    0.08
    ä»»åĬ¡æĺ¯
    0.08
    Activations Density 0.019%

    No Known Activations