© 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. 25462
    Prev
    Next
    INDEX
    Explanations

    trust and judgment

    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
    ervi
    -0.10
     retribu
    -0.08
    asad
    -0.08
    wod
    -0.08
    ampak
    -0.08
    ä¸ŃæĸĩçīĪ
    -0.08
    ongan
    -0.08
    çĶ¨å¾®ä¿¡
    -0.08
     Legislat
    -0.08
    æĥ³æĸ¹
    -0.08
    POSITIVE LOGITS
     trusted
    0.14
     trustworthy
    0.13
    trusted
    0.12
    åĢ¼å¾Ĺä¿¡èµĸ
    0.12
    æĿĥå¨ģ
    0.12
    åı¯éĿłæĢ§
    0.12
     reliable
    0.12
     trusting
    0.12
     reliability
    0.12
     unreliable
    0.11
    Activations Density 0.098%

    No Known Activations