© 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. 41482
    Prev
    Next
    INDEX
    Explanations

    metaphysical, paranormal, or mystical topics

    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
     tweeted
    -0.09
    èİİ士
    -0.08
     obliga
    -0.08
    ÏģÎŃ
    -0.07
    åł
    -0.07
     economists
    -0.07
     legislat
    -0.07
     elog
    -0.07
    :title
    -0.07
    æķ°æį®ç»ĵæŀĦ
    -0.07
    POSITIVE LOGITS
     paranormal
    0.10
     mystical
    0.10
     alleged
    0.10
     beliefs
    0.09
    èĩªç§°
    0.09
    åı¯ä¿¡
    0.09
    æīĢè°ĵçļĦ
    0.09
     belief
    0.09
    ç¥ŀç§ĺ
    0.09
    çİĦ
    0.09
    Activations Density 0.198%

    No Known Activations