© 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. 33945
    Prev
    Next
    INDEX
    Explanations

    playing cards, combinations, or sequences

    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
    Leaks
    -0.08
     Butt
    -0.08
    butt
    -0.07
    åİ»ä½ķ
    -0.07
    atalog
    -0.07
    çĻ¾äºº
    -0.07
    tape
    -0.07
    ilat
    -0.07
    åij¨ä¸ī
    -0.07
    keypress
    -0.07
    POSITIVE LOGITS
    ãĥ¬ãĥ«
    0.07
    Õ¡Õ®
    0.07
    è°ĭ
    0.07
    çĪIJ
    0.07
     progression
    0.07
     ladder
    0.07
     combinations
    0.07
     Combination
    0.07
     consolation
    0.07
     combin
    0.07
    Activations Density 0.010%

    No Known Activations