© 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. 13693
    Prev
    Next
    INDEX
    Explanations

    questions about actions or conditions

    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
    å·©
    -0.08
    ourt
    -0.08
    æĬĬä¸Ģ个
    -0.07
    以身
    -0.07
    odox
    -0.07
    (CultureInfo
    -0.07
    embe
    -0.07
    ocie
    -0.07
    æĬķèµĦæĪĸæݧèĤ¡
    -0.07
    _constant
    -0.07
    POSITIVE LOGITS
     unless
    0.09
     automatically
    0.09
    çħ§æł·
    0.09
    享æľī
    0.09
     whatever
    0.09
    éĻ¤éĿŀ
    0.09
     whichever
    0.08
    å¦Ĥæŀľè¢«
    0.08
     thereafter
    0.08
     automatic
    0.08
    Activations Density 0.091%

    No Known Activations