© 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. 63293
    Prev
    Next
    INDEX
    Explanations

    "Religious", "e.g. Bad Religion"

    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
    .eof
    -0.08
    æīĺ
    -0.08
    ëıĮ
    -0.07
     vyš
    -0.07
    ä»»ä½ķä¸ľè¥¿
    -0.07
    ictory
    -0.07
    顺é£İ
    -0.07
    éĢĨ
    -0.07
    æľ±åħĥ
    -0.07
    enade
    -0.07
    POSITIVE LOGITS
    æĤ¨åı¯èĥ½
    0.07
    ATCH
    0.07
    éĦĻ
    0.07
    wiek
    0.07
    alist
    0.07
    omor
    0.07
    æ¼Ĥ
    0.07
    ä¸Ĭæĸ°
    0.07
    apta
    0.07
    rados
    0.06
    Activations Density 0.579%

    No Known Activations