© 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. 63916
    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
    ablanca
    -0.06
    ä¸ĢåIJij
    -0.06
    alc
    -0.06
    TRO
    -0.06
     fruitful
    -0.06
    åŃ¦ä¹łæĪIJ绩
    -0.06
    å¼ķ导幼åĦ¿
    -0.06
    ç¯Ħ
    -0.05
    /cms
    -0.05
     stra
    -0.05
    POSITIVE LOGITS
    ertype
    0.08
    áŁĤ
    0.08
    lade
    0.08
    å¹´åįĬ
    0.08
    lasse
    0.07
    rina
    0.07
    estar
    0.07
    å°ĶèĴĻ
    0.07
    >Show
    0.07
    为主
    0.07
    Activations Density 0.139%

    No Known Activations