© 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. 34364
    Prev
    Next
    INDEX
    Explanations

    missing integers or sequence gaps

    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
    avers
    -0.08
    vars
    -0.07
    çī¹æľĹ
    -0.07
    åĮĹ京å¸Ĥæµ·æ·ĢåĮº
    -0.07
    chers
    -0.07
    lib
    -0.07
    åıĪåĪ°äºĨ
    -0.07
    çľ¼è§Ĵ
    -0.07
    utures
    -0.07
    å·´å·´
    -0.07
    POSITIVE LOGITS
    missing
    0.07
    ç³»ç»Ł
    0.07
    oard
    0.07
    æŁ¥æ¼ı补缺
    0.07
     Mines
    0.07
    <size
    0.07
    ä½ĵç³»
    0.07
    arged
    0.07
    -size
    0.07
    éĺ¶
    0.07
    Activations Density 0.007%

    No Known Activations