© 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. 58200
    Prev
    Next
    INDEX
    Explanations

    intentionality and knowing action

    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
    纶
    -0.08
    ocol
    -0.08
    æİ
    -0.07
     diras
    -0.07
    èij¡
    -0.07
    entina
    -0.07
    绾ç»İä¸įç»Ŀ
    -0.07
     suci
    -0.07
    足迹
    -0.07
    ìĪ
    -0.07
    POSITIVE LOGITS
    æĺİçŁ¥
    0.09
     deliberate
    0.08
    æķħæĦıçļĦ
    0.08
    æķħæĦı
    0.08
    jah
    0.08
     knowingly
    0.08
     intentional
    0.08
    åĶĨ
    0.07
    è¦ģ害
    0.07
    lob
    0.07
    Activations Density 0.007%

    No Known Activations