© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9118
    Prev
    Next
    INDEX
    Explanations

    human behavior and motivations

    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
     prestig
    -0.08
    ÑİÑĢи
    -0.07
    åı¸æ³ķé£İéĻ©
    -0.07
    çļĦä¸Ģå¤Ħ
    -0.07
     Besar
    -0.07
    ambo
    -0.07
     меÑĢÑĤ
    -0.07
    icata
    -0.07
    è§Ĩè§īæķĪæŀľ
    -0.07
     circul
    -0.07
    POSITIVE LOGITS
     behavior
    0.12
     behaviour
    0.10
    è¡Į为
    0.10
     Behavior
    0.10
     behavioral
    0.09
    behavior
    0.09
     motivations
    0.09
    è¡Į为çļĦ
    0.09
     decision
    0.09
    çļĦè¡Į为
    0.09
    Activations Density 0.060%

    No Known Activations