© 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. 23819
    Prev
    Next
    INDEX
    Explanations

    figure references

    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
    çıŃ
    -0.07
    æģ°
    -0.07
    UZ
    -0.06
    ogas
    -0.06
    æľªæľī
    -0.06
    ä¼ģä¸ļæĸ°éĹ»
    -0.06
    尿裤
    -0.06
    æIJŃ
    -0.06
     kent
    -0.06
    Ñĭз
    -0.06
    POSITIVE LOGITS
    两ä¸į误
    0.08
    Disposition
    0.08
    åįģäºĮæĿ¡
    0.07
    pagen
    0.07
    ÑĢÑĥп
    0.07
    nhard
    0.07
    atur
    0.07
    XObject
    0.07
    æĭĽèģĺç½ij
    0.07
    .").
    0.07
    Activations Density 0.009%

    No Known Activations