© 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. 43281
    Prev
    Next
    INDEX
    Explanations

    capacity, phase, world, event, six

    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
    åıŃ
    -0.07
    _unix
    -0.06
    Newton
    -0.06
     uptime
    -0.06
    æĬĺ
    -0.06
    bens
    -0.06
    los
    -0.06
     averaging
    -0.06
    æĹłåıį
    -0.06
    kilde
    -0.06
    POSITIVE LOGITS
    容纳
    0.09
     вмеÑģÑĤ
    0.09
    Capacity
    0.09
    imap
    0.08
     Capacity
    0.08
    容éĩıçļĦ
    0.08
     capacity
    0.08
    capacity
    0.08
    ElementType
    0.08
    已满
    0.08
    Activations Density 0.001%

    No Known Activations