© 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. 32646
    Prev
    Next
    INDEX
    Explanations

    after punctuation or special characters

    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
    ablo
    -0.08
    zers
    -0.08
    zer
    -0.08
    ä¸Ģæİ¢
    -0.07
    Disposition
    -0.07
    äºīä¼ĺ
    -0.07
    umbuh
    -0.07
    esseract
    -0.07
    夫人
    -0.07
    zens
    -0.07
    POSITIVE LOGITS
    ×ŀ×Ļ×Ŀ
    0.06
    iero
    0.06
    æĬĬè¿Ļ个
    0.06
    oren
    0.06
    æĸ°è§Ħå®ļ
    0.06
    roc
    0.06
    仪
    0.06
    Rew
    0.06
    触
    0.06
    åı¤
    0.06
    Activations Density 0.003%

    No Known Activations