© 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. 9435
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     proportional
    -0.07
    ismatic
    -0.06
    æľī为
    -0.06
    åIJijæĹ¥
    -0.06
     either
    -0.06
    ä¸įæį¢
    -0.06
    æ¯Ķä¾ĭ为
    -0.06
    æ±Ĥæĺ¯
    -0.06
     doc
    -0.06
    åħij
    -0.06
    POSITIVE LOGITS
    tics
    0.09
    phia
    0.09
    gne
    0.08
    lotte
    0.08
    æĹłå¤Ħ
    0.08
    rics
    0.08
    byname
    0.08
    转èĩª
    0.07
    prefix
    0.07
    Prefix
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.