© 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. 56374
    Prev
    Next
    INDEX
    Explanations

    "departure", "locked", "pointed", "little", "schizophrenia", "neutrality"

    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
    äºİæĺ¯
    -0.08
     costum
    -0.07
    ä¸įç®Ģåįķ
    -0.07
    _WARNINGS
    -0.07
     Guerrero
    -0.07
    ç¥Ŀç¦ıä½ł
    -0.07
    äºİæĺ¯ä»ĸ
    -0.07
    æĸ¼æĺ¯
    -0.07
    .meta
    -0.07
    CID
    -0.07
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.09
     padahal
    0.08
    -inst
    0.08
     Padahal
    0.07
    æł¹æľ¬ä¸įæĺ¯
    0.07
    å®ŀåĪĻ
    0.07
    èĢĮæĺ¯
    0.07
     Instead
    0.07
     instead
    0.07
    åıįèĢĮæĺ¯
    0.07
    Activations Density 0.004%

    No Known Activations