© 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. 10876
    Prev
    Next
    INDEX
    Explanations

    options or decisions

    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
    漿
    -0.08
     tenden
    -0.07
    æµĨ
    -0.07
     übrigens
    -0.07
     terecht
    -0.07
    OMET
    -0.07
    ometimes
    -0.07
    人æĪĸ
    -0.07
    jord
    -0.07
    ãģĦãģŁãĤĬ
    -0.07
    POSITIVE LOGITS
    å½ĵæŶ
    0.13
    å½ĵæŶçļĦ
    0.13
    åľ¨å½ĵæŶ
    0.12
     someday
    0.11
     möglichst
    0.11
     devait
    0.10
    å½ĵæĻĤ
    0.10
    çķ¶æĻĤ
    0.10
     debÃŃa
    0.10
    æĹ¢èĥ½
    0.10
    Activations Density 1.085%

    No Known Activations