© 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. 51373
    Prev
    Next
    INDEX
    Explanations

    integral signs

    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
     patent
    -0.06
    ði
    -0.06
    tha
    -0.06
    agno
    -0.06
    æľĢä¼Łå¤§çļĦ
    -0.06
    æĵ
    -0.06
     zlib
    -0.05
    ì°©
    -0.05
    åľ¨åģļ好
    -0.05
    á»iji
    -0.05
    POSITIVE LOGITS
    reau
    0.08
    frared
    0.08
     _$
    0.08
    ער
    0.07
    echt
    0.07
    èĮĥåĽ´åĨħ使çĶ¨
    0.07
    otp
    0.07
    eree
    0.07
    ofday
    0.07
    chimp
    0.07
    Activations Density 0.004%

    No Known Activations