© 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. 46661
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
    åijµ
    -0.07
    UTA
    -0.06
     Awakening
    -0.06
    åħĪåĪ°
    -0.06
    ×ķ×IJ
    -0.06
    _extended
    -0.06
    able
    -0.06
    data
    -0.06
    æľīäºĽä¸į
    -0.06
     Mormon
    -0.05
    POSITIVE LOGITS
    è¯ŃéŁ³æŶéķ¿
    0.08
    essus
    0.08
    âĨĵâĨĵ
    0.08
    goci
    0.08
    -peer
    0.08
    ]+'
    0.08
    ائب
    0.08
    toor
    0.07
    adge
    0.07
    leftright
    0.07
    Activations Density 0.015%

    No Known Activations