© 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. 13558
    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
    ÑĤаÑĢ
    -0.07
    Scalars
    -0.07
    [`
    -0.07
    åĽ¢æĪIJåijĺ
    -0.07
    ä¸įåĽł
    -0.07
    ä¸įåıij
    -0.07
    legen
    -0.07
     lá»ģ
    -0.07
    ÑĤеÑĢ
    -0.07
    asca
    -0.06
    POSITIVE LOGITS
    izzo
    0.09
    irm
    0.08
    iffe
    0.06
    irez
    0.06
    .so
    0.06
    اÙĦتÙĩا
    0.06
    mentions
    0.06
    vid
    0.06
     Cru
    0.06
    ksz
    0.06
    Activations Density 0.000%

    No Known Activations