© 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. 42340
    Prev
    Next
    INDEX
    Explanations

    psoralen, Down, airstrip, wafer, wristband

    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
    kowski
    -0.08
    ÙĥÙIJ
    -0.08
     fras
    -0.07
    æľ¬èº«çļĦ
    -0.07
    elingen
    -0.07
    olon
    -0.07
    ezd
    -0.07
    ingo
    -0.07
    åĺĪ
    -0.07
    ritti
    -0.07
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.07
    çon
    0.06
    çĸ¤
    0.06
    ney
    0.06
    enda
    0.06
    ä¼ĺ
    0.05
    对该
    0.05
    are
    0.05
    ue
    0.05
    èĽ®
    0.05
    Activations Density 0.402%

    No Known Activations