© 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. 45780
    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
    usin
    -0.10
    IFY
    -0.09
    ILD
    -0.08
    ansir
    -0.08
    ÑİÑĢ
    -0.08
    enschaft
    -0.08
    ikian
    -0.08
     KEP
    -0.08
    å¾ľ
    -0.08
    enko
    -0.08
    POSITIVE LOGITS
    b
    0.07
    d
    0.07
    æĺ¾èĢĮæĺĵ
    0.06
    ie
    0.06
    bill
    0.06
    ire
    0.06
    artic
    0.06
    สà¸ķิ
    0.06
    ç´¯
    0.06
    iris
    0.06
    Activations Density 0.000%

    No Known Activations