© 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. 39750
    Prev
    Next
    INDEX
    Explanations

    risk, utility, and decision-making

    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
    ecam
    -0.09
    äºĭå®ŀè¯ģæĺİ
    -0.08
    è¹Ń
    -0.08
    èĩªè¾¾
    -0.07
     Giunta
    -0.07
    yez
    -0.07
    chow
    -0.07
    åĨł
    -0.07
     spur
    -0.07
    åĭ¤
    -0.07
    POSITIVE LOGITS
    åģı好
    0.09
     hed
    0.08
    åİĮæģ¶
    0.08
    -risk
    0.08
     psychologically
    0.08
    çļĦå¿ĥçIJĨ
    0.08
     preferences
    0.08
    è´´çİ°
    0.08
    å¿ĥçIJĨ
    0.08
     psychological
    0.08
    Activations Density 0.008%

    No Known Activations