© 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. 23559
    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
    éĨ
    -0.07
     Wise
    -0.06
    ç¿ĺ
    -0.06
    aine
    -0.06
    alia
    -0.06
    çŃ·åŃIJ
    -0.06
     Herm
    -0.06
    æĬ¹
    -0.06
    æľĿé²ľ
    -0.06
    涨
    -0.06
    POSITIVE LOGITS
    容
    0.09
    rames
    0.08
    rame
    0.08
    alisi
    0.08
    çĴIJ
    0.08
    iky
    0.08
    achten
    0.08
    .ibm
    0.08
    åIJł
    0.08
     å¼ķçĶ¨
    0.08
    Activations Density 0.000%

    No Known Activations