© 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. 12191
    Prev
    Next
    INDEX
    Explanations

    pathway notation

    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
     Hamp
    -0.07
    ff
    -0.06
    ajt
    -0.06
     divided
    -0.06
    ody
    -0.06
    trum
    -0.06
    åĪĨäºĨ
    -0.06
     Frank
    -0.06
     conforms
    -0.06
    ·
    -0.05
    POSITIVE LOGITS
    è·¯å¾Ħ
    0.09
    éĢĶå¾Ħ
    0.09
    ugier
    0.09
    éĵ¾è·¯
    0.08
    åĢŁåĬĽ
    0.08
    çļĦè·¯
    0.08
    éĽĢ
    0.08
    æĬĦ
    0.08
    -hop
    0.08
    Invoker
    0.08
    Activations Density 0.006%

    No Known Activations