© 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. 65532
    Prev
    Next
    INDEX
    Explanations

    FDI

    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
    Ð¢Ðł
    -0.07
    ắm
    -0.07
    çĹ´
    -0.07
    бÑĥÑĤ
    -0.07
    aret
    -0.07
    -io
    -0.06
    *dx
    -0.06
    Throwable
    -0.06
     distrib
    -0.06
    çıĪ
    -0.06
    POSITIVE LOGITS
    ãĥ©ãĥ«
    0.08
    æ§Ľ
    0.08
    uum
    0.08
    è¿ľé«ĺäºİ
    0.08
    èIJ¨æĸ¯
    0.08
     accessibile
    0.07
    æĽ¿å°¼
    0.07
    å±Ĥ次çļĦ
    0.07
    åįİé¾Ļ
    0.07
     tunes
    0.07
    Activations Density 0.006%

    No Known Activations