© 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. 57071
    Prev
    Next
    INDEX
    Explanations

    components and materials

    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
     according
    -0.07
    γάλ
    -0.06
    çļĦæīĭä¸Ń
    -0.06
    åĴĮé»Ħ
    -0.06
    reten
    -0.06
    êu
    -0.06
    én
    -0.06
    égard
    -0.06
     Reds
    -0.06
    å®ĥ们æĺ¯
    -0.06
    POSITIVE LOGITS
     плÑİÑģ
    0.10
    人被
    0.10
    åįķä½įåıĤåĬł
    0.10
    ç³»ç»Łä¸İ
    0.10
    è®°èĢħåľ¨
    0.09
    åĨįåĬłä¸Ĭ
    0.09
     plus
    0.09
    éĥ¨éŨèģĶåIJĪ
    0.09
    è¿ŀåIJĮ
    0.09
    çļĦäººåľ¨
    0.09
    Activations Density 0.356%

    No Known Activations