© 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. 23595
    Prev
    Next
    INDEX
    Explanations

    biblical texts and figures

    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
    raga
    -0.09
    åĩłç§ĴéĴŁ
    -0.09
    acruz
    -0.08
     chans
    -0.08
    çĶŁç´ł
    -0.08
     ÏĨι
    -0.07
    rag
    -0.07
    .pol
    -0.07
    äf
    -0.07
     sahab
    -0.07
    POSITIVE LOGITS
     Hebrew
    0.09
    èĢ¶åĴĮåįİ
    0.09
    Scroll
    0.09
     cedar
    0.09
     Israel
    0.09
     Jerusalem
    0.08
     Lebanon
    0.08
     covenant
    0.08
     Yah
    0.08
     Eph
    0.08
    Activations Density 0.043%

    No Known Activations