© 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. 9523
    Prev
    Next
    INDEX
    Explanations

    and/or conditions

    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
    åħ¶äºº
    -0.08
    è¿Ļ个æķ°åŃĹ
    -0.07
    åħ¨éĥ¨è¯Ħ论
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    IAS
    -0.07
     Schon
    -0.07
    æľĢæĸ°æĸĩç«ł
    -0.07
    rieben
    -0.07
    urch
    -0.07
    msp
    -0.07
    POSITIVE LOGITS
     conditions
    0.09
     clauses
    0.08
    æĿ¡ä»¶åĴĮ
    0.08
     clause
    0.08
    æľīæĿ¡ä»¶
    0.08
     condition
    0.08
    æĿ¡ä»¶
    0.08
    ault
    0.07
     Conditions
    0.07
     Clause
    0.07
    Activations Density 0.006%

    No Known Activations