© 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. 1165
    Prev
    Next
    INDEX
    Explanations

    citation markers like [@B1]

    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
    çĻ½
    -0.07
    è¦ģä¹Īæĺ¯
    -0.06
    edic
    -0.06
     Either
    -0.06
    Either
    -0.06
    è¦ģä¹Ī
    -0.06
    å®ļ
    -0.06
    rea
    -0.06
    æĻ
    -0.06
     either
    -0.06
    POSITIVE LOGITS
    TEL
    0.08
     Soc
    0.08
    resso
    0.08
    è¿ĺåħ·æľī
    0.08
    çļĦè¿ĺæľī
    0.08
    è¿ĺåı¯èĥ½
    0.08
    baugh
    0.07
    è¿ĺæľīä¸ĢäºĽ
    0.07
    째
    0.07
    社ä¼ļä¸Ĭ
    0.07
    Activations Density 0.001%

    No Known Activations