© 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. 43157
    Prev
    Next
    INDEX
    Explanations

    martyrs and persecution

    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
     kling
    -0.07
     ticks
    -0.07
     contrat
    -0.07
     prést
    -0.07
    å¤§æľ¬
    -0.07
    /--
    -0.07
     Rousse
    -0.07
    æĿ¨æŁ³
    -0.07
    çais
    -0.07
     Berlusconi
    -0.07
    POSITIVE LOGITS
    æ®ī
    0.09
     persecution
    0.09
     marty
    0.08
     persecuted
    0.08
     eyewitness
    0.08
     apost
    0.08
    æĹ©æľŁ
    0.08
    ekk
    0.08
     martyr
    0.08
     bishops
    0.08
    Activations Density 0.053%

    No Known Activations