© 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. 29705
    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
    ç½ijåıĭè¯Ħ论
    -0.08
    omit
    -0.08
    管çļĦ
    -0.07
    ä¹±ä¸ĥåħ«ç³Ł
    -0.07
    ymbols
    -0.07
     мел
    -0.07
    ùa
    -0.07
    à¤łà¥Ģ
    -0.07
     nonsense
    -0.07
    bucks
    -0.07
    POSITIVE LOGITS
    祺
    0.07
    并éĩį
    0.06
    cir
    0.06
     ::
    0.06
     Tew
    0.06
    illar
    0.06
    /raw
    0.06
    è´Łè´£åIJĮå¿Ĺ
    0.06
    便被
    0.06
    æľªå®Įå¾ħç»Ń
    0.06
    Activations Density 0.000%

    No Known Activations