© 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. 23064
    Prev
    Next
    INDEX
    Explanations

    clarification of meaning or definition

    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
    اض
    -0.08
    æľīæĥħ
    -0.08
    ä½Ĩæĺ¯çİ°åľ¨
    -0.08
    evers
    -0.08
    åŁºåľ°å»ºè®¾
    -0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.08
    åıĭ
    -0.07
    åĢºåĪ¸ä¿¡æģ¯
    -0.07
    arges
    -0.07
    gai
    -0.07
    POSITIVE LOGITS
    çļĦå®ļä¹ī
    0.11
     definition
    0.11
     definitions
    0.10
    å®ļä¹īçļĦ
    0.10
    Definition
    0.10
     defined
    0.10
    å®ļä¹ī
    0.10
    å®ļä¹ī为
    0.10
     Definition
    0.09
    defined
    0.09
    Activations Density 0.156%

    No Known Activations