© 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. 40077
    Prev
    Next
    INDEX
    Explanations

    technical parameters and biological processes

    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
    Âł
    -0.06
    icip
    -0.06
    âĢ¦
    -0.06
     _
    -0.06
    erca
    -0.06
    æ´ĭ
    -0.05
     TL
    -0.05
     اÙĦÙħÙĨ
    -0.05
     quelque
    -0.05
    edere
    -0.05
    POSITIVE LOGITS
    ä¹Łä¸Ģæł·
    0.10
    åĪĻæĺ¯
    0.10
    ä¹ŁåIJĮæł·
    0.09
    çŃīåħ¶ä»ĸ
    0.09
     likewise
    0.09
    äºijéľĦ
    0.09
    åĪĻéľĢè¦ģ
    0.09
    åĪĻå°Ĩ
    0.09
    ä¹Łæĺ¯ä¸Ģæł·
    0.09
     hingegen
    0.09
    Activations Density 0.025%

    No Known Activations