© 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. 25431
    Prev
    Next
    INDEX
    Explanations

    ostensibly legitimate but secretly false

    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
    æ¢ĵ
    -0.09
    人çľĭè¿ĩ
    -0.09
    vell
    -0.07
    ahi
    -0.07
    celli
    -0.07
    çī¹æĸ¯
    -0.07
    çĶŁäº§çĶŁæ´»
    -0.07
    éĹ®åĮ»çĶŁ
    -0.07
    answered
    -0.07
    avax
    -0.07
    POSITIVE LOGITS
     falsely
    0.13
     ÑıкобÑĭ
    0.12
     legitimate
    0.11
     ostensibly
    0.11
     guise
    0.11
    çľĭä¼¼
    0.11
     false
    0.10
    èĻļåģĩ
    0.10
    çļĦåIJįä¹ī
    0.10
     Genuine
    0.10
    Activations Density 0.241%

    No Known Activations