© 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. 32933
    Prev
    Next
    INDEX
    Explanations

    guid or belonging

    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
    uality
    -0.10
    ially
    -0.10
    uous
    -0.08
    ored
    -0.08
    cape
    -0.08
    åħ¼æĢ»ç»ıçIJĨ
    -0.08
    ldr
    -0.07
    å¤ł
    -0.07
    ãģĤãĤĮãģ°
    -0.07
    راÙĪÙĬ
    -0.07
    POSITIVE LOGITS
    (gui
    0.11
    iect
    0.09
    Ùĩ
    0.09
    orgeous
    0.09
    aison
    0.08
    ie
    0.08
    大ä¸ļ
    0.08
    angg
    0.07
    à¥įह
    0.07
    itech
    0.07
    Activations Density 0.001%

    No Known Activations