© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2287
    Prev
    Next
    INDEX
    Explanations

    gases, liquid, signal, data, testosterone

    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
    ä¸įåİĮ
    -0.06
     solo
    -0.06
    -0.06
     Nam
    -0.05
     gel
    -0.05
    çľĭæĿ¥
    -0.05
    æ²Ľ
    -0.05
    nTo
    -0.05
     toen
    -0.05
    inded
    -0.05
    POSITIVE LOGITS
     rá»ĵi
    0.10
    çĦ¶åIJİçĶ¨
    0.09
    çĦ¶åIJİåľ¨
    0.09
    çĦ¶åIJİ
    0.09
    继èĢĮ
    0.09
     سپس
    0.08
    çĦ¶åIJİå°Ĩ
    0.08
    çĦ¶åIJİå°±
    0.08
    ocker
    0.08
    .Then
    0.08
    Activations Density 0.173%

    No Known Activations