© 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. 30340
    Prev
    Next
    INDEX
    Explanations

    keyboard input and controls

    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
    é»ijçľ¼åľĪ
    -0.09
     picturesque
    -0.07
    缮ä¸Ń
    -0.07
    иÑĤелÑĮÑģÑĤво
    -0.07
    çľ¼åħī
    -0.07
     chased
    -0.06
     оÑĤÑģÑĤа
    -0.06
    ductor
    -0.06
    è·ijå¾Ĺ
    -0.06
    éģĵå·¥åºı
    -0.06
    POSITIVE LOGITS
    è¾ĵåħ¥
    0.10
    åĬ¨ä½ľ
    0.10
     input
    0.10
     tactile
    0.10
    input
    0.10
    æĮīéĶ®
    0.10
     inputs
    0.09
    è¾ĵåħ¥çļĦ
    0.09
    <input
    0.09
     buttons
    0.09
    Activations Density 0.300%

    No Known Activations