© 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. 30514
    Prev
    Next
    INDEX
    Explanations

    one of

    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
     frame
    -0.06
    å¸ľ
    -0.06
    away
    -0.06
    ---
    -0.06
    ä¸Ģ个个
    -0.06
    --
    -0.06
    丽èIJį
    -0.06
    frame
    -0.06
    åıĪæĪĸèĢħ
    -0.06
     contrast
    -0.06
    POSITIVE LOGITS
    ","","
    0.10
    )","
    0.09
    ++,
    0.08
    é¦ĸ
    0.08
     íķĺëĤĺëĬĶ
    0.08
    ä¸Ģæĺ¯
    0.08
    çĦ¶æĺ¯
    0.08
     ÑģобÑģÑĤвенно
    0.08
    isans
    0.08
    )(__
    0.07
    Activations Density 0.113%

    No Known Activations