© 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. 19299
    Prev
    Next
    INDEX
    Explanations

    research and psychological studies

    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
    çĸ«çĹħ
    -0.07
     technically
    -0.07
    æ³ķå¾ĭ顾éĹ®
    -0.07
     à¤Ĺा
    -0.07
    产ä¸ļä½ĵç³»
    -0.07
    @dynamic
    -0.07
    uff
    -0.07
    çĹħæŃ»
    -0.07
     pork
    -0.07
     artisan
    -0.07
    POSITIVE LOGITS
     psychologists
    0.14
    å¿ĥçIJĨåѦ
    0.13
     psychologist
    0.13
    å¿ĥçIJĨåŃ¦å®¶
    0.12
     behavioral
    0.12
     psychological
    0.11
    psych
    0.11
     psych
    0.11
    Psych
    0.11
     Psychology
    0.11
    Activations Density 0.775%

    No Known Activations