© 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. 32000
    Prev
    Next
    INDEX
    Explanations

    research project, authors assessed

    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
    系主任
    -0.08
     grav
    -0.07
    vus
    -0.07
    æĥħç¼ĺ
    -0.06
    管çIJĨåѦéĻ¢
    -0.06
    cape
    -0.06
    onga
    -0.06
     tease
    -0.06
    Core
    -0.06
    sender
    -0.06
    POSITIVE LOGITS
    æ¯ı天éĥ½åľ¨
    0.08
    laki
    0.08
    åĨįåģļ
    0.08
     lagi
    0.08
    irectory
    0.07
    crement
    0.07
    å¼ĢåĬ¨
    0.07
     Permit
    0.07
    åĨį说
    0.07
    erview
    0.07
    Activations Density 0.001%

    No Known Activations