© 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. 34314
    Prev
    Next
    INDEX
    Explanations

    demonstrates existence or attainability

    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
    λεÏį
    -0.08
    aved
    -0.08
    ضاÙĨ
    -0.08
    letal
    -0.07
    çĶŁåij½çº¿
    -0.07
     >::
    -0.07
     ÑĢазвод
    -0.07
    umbang
    -0.07
    keit
    -0.07
    urnal
    -0.07
    POSITIVE LOGITS
    个çĤ¹
    0.06
     satisfy
    0.06
     menger
    0.06
    å¤ļç§įæĸ¹å¼ı
    0.06
    Localization
    0.06
    omu
    0.06
     somewhere
    0.06
    çļĦæĥħæĢĢ
    0.06
    -seeking
    0.06
     closure
    0.06
    Activations Density 0.004%

    No Known Activations