© 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. 24478
    Prev
    Next
    INDEX
    Explanations

    and investments

    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
    inary
    -0.07
    åıĶ
    -0.07
    天çĦ¶çļĦ
    -0.06
    æ¡Ķ
    -0.06
    ÑĤока
    -0.06
    m
    -0.06
     campaigning
    -0.06
     Ñĥви
    -0.06
    çĻ½æĿ¡
    -0.06
    à¹ģหล
    -0.06
    POSITIVE LOGITS
     Morton
    0.08
    Äħż
    0.08
    amen
    0.08
    olis
    0.08
    æĸ°ç½ij
    0.07
    {return
    0.07
    hares
    0.07
    oler
    0.07
    æºľæºľ
    0.07
    itorium
    0.07
    Activations Density 0.017%

    No Known Activations