© 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. 14992
    Prev
    Next
    INDEX
    Explanations

    testing or checking

    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
    edig
    -0.07
    ajat
    -0.07
    enic
    -0.07
    wiat
    -0.07
    ä¸ĢæĿij
    -0.06
    erar
    -0.06
    enade
    -0.06
    prises
    -0.06
    ajt
    -0.06
    å·¡è§Ĩåijĺ
    -0.06
    POSITIVE LOGITS
    ån
    0.07
    æ··
    0.07
     Angr
    0.07
    пл
    0.07
    åħ·
    0.07
    太éĥİ
    0.06
    ervi
    0.06
    çıĢ
    0.06
     Ùģرا
    0.06
    icch
    0.06
    Activations Density 0.026%

    No Known Activations