© 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. 13104
    Prev
    Next
    INDEX
    Explanations

    trust

    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
    ³
    -0.08
    isms
    -0.07
    eration
    -0.07
     СÑĤаÑĤÑĮ
    -0.07
    Ŀ
    -0.07
    หà¸Ļà¹īาà¸Ļีà¹ī
    -0.07
    ¶
    -0.07
    æĥ³å¾ĹåĪ°
    -0.07
    ugno
    -0.07
    жава
    -0.07
    POSITIVE LOGITS
    worth
    0.13
    worthy
    0.12
    æľīåĬł
    0.09
     trust
    0.09
    ingly
    0.09
    ä¿¡ä»»
    0.09
    æīĺä»ĺ
    0.09
    fulness
    0.09
    ful
    0.09
    èݱåĿŀ
    0.09
    Activations Density 0.018%

    No Known Activations