© 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. 61485
    Prev
    Next
    INDEX
    Explanations

    confirmation questions

    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
    çĶļèĢħ
    -0.08
    å±
    -0.07
    év
    -0.07
    REATE
    -0.07
    è¦ģéĢīæĭ©
    -0.07
     navÃŃc
    -0.07
    гÑĢаÑĦ
    -0.07
    bose
    -0.07
    bage
    -0.07
    æĢ
    -0.07
    POSITIVE LOGITS
    adu
    0.08
    ook
    0.07
     âľĶ
    0.06
    åIJĮæĹ¥
    0.06
     ë§ŀ
    0.06
    éĢļãĤĬ
    0.06
    ENA
    0.06
     sparing
    0.06
    æĺ¯å¯¹çļĦ
    0.06
    æĺ¯æŃ£ç¡®çļĦ
    0.06
    Activations Density 0.001%

    No Known Activations