© 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. 47270
    Prev
    Next
    INDEX
    Explanations

    Edit and follow-up clarification

    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
    leven
    -0.07
    iab
    -0.07
    alfa
    -0.07
    oodoo
    -0.07
    uess
    -0.07
    ặn
    -0.07
    usan
    -0.07
    enius
    -0.07
    eler
    -0.07
    cesa
    -0.07
    POSITIVE LOGITS
    atap
    0.07
    íģ¬
    0.06
    _chain
    0.06
    ä¸įä»ħå¦ĤæѤ
    0.06
    aya
    0.06
    hh
    0.06
    åıªæĺ¯ä¸Ģ个
    0.06
    æł¹æľ¬ä¸Ĭ
    0.06
    omatic
    0.06
    Turn
    0.06
    Activations Density 0.001%

    No Known Activations