© 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. 63198
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    кеÑĤа
    -0.07
    stö
    -0.07
    aline
    -0.07
     reng
    -0.07
    ific
    -0.07
    çĵľæŀľ
    -0.07
    wesen
    -0.06
    家åºŃç»ıæµİ
    -0.06
    ager
    -0.06
    æīĵäºĨ个
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.08
     ahead
    0.08
    adden
    0.07
    cision
    0.07
    å¹²çļĦ
    0.07
    åīįéĿ¢
    0.07
    åľ¨åīįéĿ¢
    0.07
    hung
    0.07
    ingham
    0.07
    æ®ĭ
    0.07
    Activations Density 0.000%

    No Known Activations