© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62867
    Prev
    Next
    INDEX
    Explanations

    dangerous or danger

    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
    _stderr
    -0.09
    à¸Ĥาว
    -0.09
    åĶ§
    -0.09
    ukum
    -0.08
    æµ·é»ĺ
    -0.08
    variably
    -0.08
    ä¾ĨçļĦ
    -0.08
    缼äºĭ
    -0.08
    StackTrace
    -0.08
     pau
    -0.08
    POSITIVE LOGITS
    ous
    0.09
    ously
    0.08
    éĩįéĩįçļĦ
    0.08
    à¸łà¸±à¸¢
    0.08
     hiá»ĥm
    0.08
    æĢ§çļĦ
    0.08
    éĩįéĩį
    0.07
    ness
    0.07
    osamente
    0.07
     posed
    0.07
    Activations Density 0.015%

    No Known Activations