© 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. 8644
    Prev
    Next
    INDEX
    Explanations

    Greg, GNU, POSIX, STL, system

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    åħ³éĶ®çݯèĬĤ
    -0.08
    æĬĺä¸į
    -0.08
    ACHER
    -0.08
    eated
    -0.08
    .loadData
    -0.08
    åľºåĿĩ
    -0.08
    åĥıä½ł
    -0.08
    ÅĽni
    -0.08
    ellas
    -0.08
    schap
    -0.08
    POSITIVE LOGITS
    ®
    0.07
    .org
    0.07
    ä¸ŃæľĢ
    0.07
    -compatible
    0.07
    -derived
    0.07
    åĴĮä¸ŃåĽ½
    0.07
    0.07
    åĪ¶
    0.06
    åĴĮç¾İåĽ½
    0.06
    ä¸ŃçļĦåľ°ä½į
    0.06
    Activations Density 0.004%

    No Known Activations