© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2858
    Prev
    Next
    INDEX
    Explanations

    register, selector, attribute, depends

    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
    麻éĽĢ
    -0.06
    orado
    -0.06
    inois
    -0.06
    áŀİ
    -0.06
     strerror
    -0.06
     overlay
    -0.06
    ebol
    -0.06
    enz
    -0.06
    olg
    -0.06
    acun
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĪĸéĹ´æİ¥
    0.09
    -license
    0.08
    athi
    0.08
    ä¸įå½Ĵ
    0.08
    éĤĥ
    0.07
    mena
    0.07
    Nr
    0.07
    ä¹İåħ¶
    0.07
    ellet
    0.07
    ç»ĪçĶŁ
    0.07
    Activations Density 0.001%

    No Known Activations