© 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. 57324
    Prev
    Next
    INDEX
    Explanations

    debate, debtor, future, member

    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
    åľ¨ç»Ļ
    -0.09
    ãĥķãĤ©ãĥ³
    -0.07
    gard
    -0.07
    è½°
    -0.07
    åįģåħ«æĿ¡
    -0.07
    .va
    -0.07
    owitz
    -0.07
    yarat
    -0.07
    achs
    -0.07
    sembly
    -0.07
    POSITIVE LOGITS
     original
    0.07
    æĽ´æŃ£
    0.07
     fours
    0.06
     accur
    0.06
    æŀ
    0.06
    Õ²
    0.06
     Original
    0.06
    æľĽ
    0.06
     orig
    0.06
    åĩĨç¡®æĢ§
    0.06
    Activations Density 0.001%

    No Known Activations