© 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. 64458
    Prev
    Next
    INDEX
    Explanations

    perception verbs

    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
    ائÙĨ
    -0.08
     Defined
    -0.08
    Defined
    -0.08
    æľīæĹł
    -0.08
    ĥĿ
    -0.07
    _defined
    -0.07
    æĬ¬
    -0.07
    ãs
    -0.07
    Ľ°
    -0.07
    aths
    -0.07
    POSITIVE LOGITS
    çĴŀ
    0.07
    æľīè¿Ļä¹Ī
    0.07
    æĺ¯ä¸ĢèĪ¬
    0.06
    dir
    0.06
    Collapse
    0.06
    æľīåħ³äºİ
    0.06
    æĪĸéĢļè¿ĩ
    0.06
     somewhat
    0.06
     vag
    0.06
     modest
    0.06
    Activations Density 0.039%

    No Known Activations