© 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. 39258
    Prev
    Next
    INDEX
    Explanations

    legislative assembly

    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
     Briggs
    -0.06
    IPP
    -0.06
    zu
    -0.06
    zy
    -0.06
    oda
    -0.06
    æ¿ĥåİļ
    -0.06
    .").
    -0.06
     chứ
    -0.06
    åįij
    -0.05
    è´¤
    -0.05
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.10
    åıĪåı«
    0.09
    addin
    0.08
    hares
    0.08
    uchia
    0.08
    <dd
    0.08
    è¿Ļæĺ¯åľ¨
    0.08
    ENTIC
    0.08
    baugh
    0.08
    è¿Ļæĺ¯å¯¹
    0.08
    Activations Density 0.006%

    No Known Activations