© 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. 27225
    Prev
    Next
    INDEX
    Explanations

    .I, .We, .Areas starts

    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
    ĥĿ
    -0.11
    综ä¸ĬæīĢè¿°
    -0.09
    estos
    -0.08
    æľĢåIJİåľ¨
    -0.08
    finally
    -0.08
    ׼×ķ׾
    -0.08
    ensos
    -0.08
    hoven
    -0.08
     finally
    -0.08
     Enfin
    -0.08
    POSITIVE LOGITS
    ↵
    0.07
    çĴŀ
    0.06
    go
    0.06
    é¦ĸåħĪ
    0.06
    ÑĢÑij
    0.06
     firstly
    0.06
    çĶ«
    0.06
     ↵
    0.06
    å·´æİĮ
    0.06
    é¦ĸåħĪåľ¨
    0.06
    Activations Density 0.021%

    No Known Activations