© 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. 12306
    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
    oire
    -0.08
    cker
    -0.08
    Ymd
    -0.07
    å®Ľ
    -0.07
    egment
    -0.07
    wa
    -0.07
    porten
    -0.07
     vigore
    -0.07
    ocken
    -0.07
    prise
    -0.07
    POSITIVE LOGITS
    ãĥ¼ãĤ¯
    0.07
    æģ°å·§
    0.07
    è¦ģæĺ¯
    0.07
     voilÃł
    0.06
    ç»ĵ对
    0.06
    âĹİ
    0.06
    èĬĤæĹ¥æľŁéĹ´
    0.06
    éĶ¦
    0.06
    ÙĤÙĩ
    0.06
    çļĦåıĮéĩį
    0.06
    Activations Density 0.000%

    No Known Activations