© 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. 17257
    Prev
    Next
    INDEX
    Explanations

    workshop location and dates

    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
    s
    -0.11
    i
    -0.11
    и
    -0.11
    er
    -0.10
    ×Ļ
    -0.09
    ÙĬ
    -0.09
    Ñĭ
    -0.09
    áĥĺ
    -0.09
    нÑĭе
    -0.09
    ãĥ³
    -0.08
    POSITIVE LOGITS
    ation
    0.10
    Ø©
    0.09
    utow
    0.09
    tedir
    0.08
    ãĤĭãģ¨
    0.08
    onstr
    0.08
    sembler
    0.08
    cw
    0.08
    ruh
    0.08
    wany
    0.08
    Activations Density 0.001%

    No Known Activations