© 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. 42631
    Prev
    Next
    INDEX
    Explanations

    seeming perception

    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
    SearchParams
    -0.08
    ç¼®
    -0.07
    .unique
    -0.07
    رÙĬØŃØ©
    -0.06
    ieder
    -0.06
    Ñĩек
    -0.06
    ugier
    -0.06
    emplates
    -0.06
     Ums
    -0.06
    predict
    -0.06
    POSITIVE LOGITS
     perceived
    0.15
     perception
    0.13
     apparent
    0.13
    éĶĻè§ī
    0.12
     aparent
    0.12
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.12
     Perception
    0.12
     seeming
    0.11
     illusion
    0.11
     perceptions
    0.11
    Activations Density 0.130%

    No Known Activations