© 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. 28133
    Prev
    Next
    INDEX
    Explanations

    often, episode, us, folks, grant, time, game, while

    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
    )?.
    -0.08
    êµī
    -0.07
    ụa
    -0.07
    egah
    -0.07
    ë´
    -0.07
    )..
    -0.07
     dimin
    -0.07
     Setia
    -0.07
    认è¯ģåķĨ家
    -0.07
    ÑģовеÑģÑĤ
    -0.07
    POSITIVE LOGITS
    åIJĦ项任åĬ¡
    0.06
    hofer
    0.06
     PA
    0.06
    ибо
    0.06
    éĽħ
    0.06
    andom
    0.06
    .exports
    0.06
    axed
    0.06
    CAF
    0.06
    å°ĬèĢħ
    0.05
    Activations Density 0.149%

    No Known Activations