© 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. 29202
    Prev
    Next
    INDEX
    Explanations

    g(z), K\cap Z(G,Y), g\in G, S=A, L is

    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
    omes
    -0.06
     __
    -0.06
     ·
    -0.06
    æĥŁ
    -0.06
    交éĽĨ
    -0.06
     Justice
    -0.06
    efault
    -0.06
    fern
    -0.06
    ÙĪÙħ
    -0.06
    «
    -0.05
    POSITIVE LOGITS
    anders
    0.09
    attery
    0.08
    azzi
    0.08
     cint
    0.07
    ears
    0.07
    ãĤ¡
    0.07
    yers
    0.07
    åıĸéķ¿è¡¥çŁŃ
    0.07
    åķıé¡Įãģ¯
    0.07
    Annotations
    0.07
    Activations Density 0.013%

    No Known Activations