© 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. 29011
    Prev
    Next
    INDEX
    Explanations

    Tigers won, Vikings, Mohigans

    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
     ip
    -0.06
    assy
    -0.06
    zan
    -0.06
     bool
    -0.06
     I
    -0.06
     information
    -0.05
     pl
    -0.05
    åħ·ä½ĵ
    -0.05
    çī¹åĪ«å¤ļ
    -0.05
    (bool
    -0.05
    POSITIVE LOGITS
     cioè
    0.08
    izu
    0.08
    æļ¨
    0.08
    hiba
    0.08
    icing
    0.08
    æĩIJ
    0.08
    amica
    0.08
    éļĪ
    0.08
    हा
    0.08
    beck
    0.08
    Activations Density 0.300%

    No Known Activations