© 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. 50206
    Prev
    Next
    INDEX
    Explanations

    dip, bath, soak, or immersion

    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
    山人
    -0.08
    éĵ²
    -0.06
    åĬĥ
    -0.06
    .dir
    -0.06
    ç¨
    -0.06
    æķ²éŨ
    -0.06
    awn
    -0.06
    æĬij
    -0.06
    åŁİéĻħ
    -0.06
    azon
    -0.06
    POSITIVE LOGITS
    浸泡
    0.14
     immersion
    0.12
    浸åħ¥
    0.11
    浸
    0.10
     soaking
    0.10
     immers
    0.09
     soak
    0.09
     baths
    0.09
    浸润
    0.09
     погÑĢÑĥ
    0.09
    Activations Density 0.111%

    No Known Activations