© 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. 56054
    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
    å®ģ
    -0.08
    VERT
    -0.07
    ctal
    -0.07
    稽
    -0.07
    ebol
    -0.07
     Dres
    -0.07
    acks
    -0.07
    èĢĮèĩ³
    -0.07
    obre
    -0.07
    åŃ¦ä¹łä¸Ĭ
    -0.07
    POSITIVE LOGITS
    gression
    0.08
    æł©
    0.07
    ìĤ¬íķŃ
    0.07
    æ±IJ
    0.07
    fulness
    0.07
    halt
    0.07
    ceived
    0.07
    lee
    0.07
    ioned
    0.07
    aging
    0.07
    Activations Density 0.000%

    No Known Activations