© 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. 46740
    Prev
    Next
    INDEX
    Explanations

    cross-sectional, cross-country, cross post

    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
    erald
    -0.09
    jenigen
    -0.09
    ullah
    -0.09
    istically
    -0.09
    errupt
    -0.08
    irst
    -0.08
    ekor
    -0.08
    комплек
    -0.08
    ysterious
    -0.08
    istic
    -0.08
    POSITIVE LOGITS
    ingly
    0.11
    s
    0.09
    i
    0.09
    ivity
    0.09
    er
    0.08
    roads
    0.08
    tures
    0.08
    bite
    0.08
    Ùĩ
    0.08
    bill
    0.08
    Activations Density 0.063%

    No Known Activations