© 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. 27808
    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
    loff
    -0.08
    afia
    -0.08
    agl
    -0.07
    æ±Ĥç²¾
    -0.07
    Ģ
    -0.07
    αιν
    -0.07
    åĽłä¸ºåħ¶
    -0.07
    ãģķãĤĬ
    -0.07
    شتÙĩ
    -0.06
     Command
    -0.06
    POSITIVE LOGITS
    éķĩéķ¿
    0.07
    åĺ¿
    0.07
    Extras
    0.07
    odable
    0.07
    /manage
    0.07
    ifiable
    0.07
    _PROVID
    0.07
    able
    0.07
    éķĸ
    0.07
    è¾Ħ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.