© 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. 2034
    Prev
    Next
    INDEX
    Explanations

    binary choice

    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
    avig
    -0.08
    éħĮ
    -0.08
     nanti
    -0.08
    çĶĦ
    -0.08
    aber
    -0.07
    дж
    -0.07
     porr
    -0.07
    ç´¢
    -0.07
    æĬĬå®ĥ们
    -0.07
    flen
    -0.07
    POSITIVE LOGITS
    ä¸ºçĽ®æłĩ
    0.08
    çļĦ追æ±Ĥ
    0.08
    ãĤĴçĭĻ
    0.08
    ãĤĴ缮æĮĩãģĻ
    0.08
    è±ļ
    0.07
    ä¸Ģ件äºĭ
    0.07
     output
    0.07
     Nose
    0.07
    reat
    0.07
    eh
    0.07
    Activations Density 0.310%

    No Known Activations