© 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. 39158
    Prev
    Next
    INDEX
    Explanations

    sports related topics

    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
    acker
    -0.07
    éĺģ
    -0.06
    urret
    -0.06
    etter
    -0.06
    éĸ£
    -0.06
    æ·±å¤ĦçļĦ
    -0.06
    æij
    -0.06
    airy
    -0.06
     workings
    -0.06
    çijŀæĭī
    -0.06
    POSITIVE LOGITS
    manship
    0.10
    åĻ¨æĿIJ
    0.09
    nasium
    0.09
    å°ijæŀĹ
    0.08
    åľºé¦Ĩ
    0.08
     feder
    0.08
    ç«ŀæĬĢ
    0.08
     sporting
    0.08
    letes
    0.08
    èĭ±å§¿
    0.08
    Activations Density 0.363%

    No Known Activations