© 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. 43876
    Prev
    Next
    INDEX
    Explanations

    letter choices

    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
    åħ·
    -0.07
    zte
    -0.07
     meanwhile
    -0.07
     ``(
    -0.07
    (World
    -0.07
    ainers
    -0.06
    ","","
    -0.06
    alem
    -0.06
    ainer
    -0.06
    宫ä¸Ń
    -0.06
    POSITIVE LOGITS
    çĺ¾
    0.08
    ãģıãĤīãģĦãģ®
    0.07
     Dancing
    0.07
    请éĢīæĭ©
    0.07
    å¿ĥæĥ³äºĭæĪIJ
    0.07
    ellular
    0.07
    计ç®Ĺæľºè½¯ä»¶
    0.06
    åħ¬å¼ĢèµĽ
    0.06
    anca
    0.06
    åľĥ
    0.06
    Activations Density 0.003%

    No Known Activations