© 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. 10063
    Prev
    Next
    INDEX
    Explanations

    faster-than-light, resurrection, death, powers, conspiracy

    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
    æ·±æµħ
    -0.08
    еÑĩе
    -0.08
    æ´ĭ
    -0.07
    寡
    -0.07
    åħ±åIJĮ
    -0.07
    иÑĢ
    -0.07
    åħ±åIJĮæĪIJéķ¿
    -0.07
     пÑĢоÑĦилÑĮ
    -0.07
    åħ±åIJĮè¿ĽæŃ¥
    -0.07
    deg
    -0.07
    POSITIVE LOGITS
    è¿Ŀåıį
    0.12
    è¿ĿèĥĮ
    0.10
    è¿ĿåıįäºĨ
    0.10
     violating
    0.10
     violates
    0.09
    éģķåıį
    0.09
     violate
    0.09
    å¦ĤæŀľçľŁçļĦ
    0.08
    Allowed
    0.08
     violation
    0.08
    Activations Density 0.047%

    No Known Activations