© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14608
    Prev
    Next
    INDEX
    Explanations

    which or who followed by a verb

    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
    bay
    -0.08
    åĪ«è¯´
    -0.08
    æīĢ以ä»ĸ们
    -0.07
    skap
    -0.07
    大æ¦Ĥå°±æĺ¯
    -0.07
    auen
    -0.07
    engen
    -0.07
    onnal
    -0.07
    é£İ顺
    -0.07
    æ½®
    -0.07
    POSITIVE LOGITS
     pourtant
    0.10
    .k
    0.09
     appunto
    0.08
     otherwise
    0.08
     przecież
    0.08
     now
    0.08
     often
    0.07
     supposedly
    0.07
     admittedly
    0.07
     presumably
    0.07
    Activations Density 0.719%

    No Known Activations