© 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. 20212
    Prev
    Next
    INDEX
    Explanations

    malignant biology

    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
    QÄIJ
    -0.07
     longe
    -0.07
    ìŀĬ
    -0.07
    coce
    -0.07
    Ñģени
    -0.07
    꽤
    -0.07
    ropa
    -0.07
    adang
    -0.07
     ëįĶ보기
    -0.07
    SK
    -0.07
    POSITIVE LOGITS
    åı·æĸĩ件
    0.08
    æĻ¤
    0.07
    ëĿ½
    0.07
    upe
    0.07
    ball
    0.06
    线ä¸İ
    0.06
    Ö¼
    0.06
    éģµ
    0.06
    .Rendering
    0.06
    unction
    0.06
    Activations Density 0.837%

    No Known Activations