© 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. 31663
    Prev
    Next
    INDEX
    Explanations

    reporting speech or information

    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
    esh
    -0.07
    æł·çļĦ
    -0.07
    è¯ķè¯ķ
    -0.07
    åij³çļĦ
    -0.07
     enc
    -0.06
    åIJİèĢħ
    -0.06
     Hung
    -0.06
    ä¸įæĪIJåĬŁ
    -0.06
    UniqueId
    -0.06
    çļĦæľĢç»Ī
    -0.06
    POSITIVE LOGITS
    .orig
    0.08
     Simply
    0.08
    upra
    0.08
    ä¸į足ä¹ĭå¤Ħ
    0.08
    Simply
    0.07
    isir
    0.07
    imson
    0.07
     Unterk
    0.07
    ëĭĺ
    0.07
    éĤ£æŶçļĦ
    0.07
    Activations Density 0.015%

    No Known Activations