© 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. 20401
    Prev
    Next
    INDEX
    Explanations

    (a) followed by punctuation

    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
    d
    -0.09
    l
    -0.09
    c
    -0.08
    v
    -0.08
    s
    -0.08
    ÙħÙĨد
    -0.08
    al
    -0.08
    x
    -0.07
    ÙĦ
    -0.07
    p
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.10
    ensored
    0.08
    并èĮĤ
    0.08
    jukan
    0.08
    alse
    0.08
    agher
    0.08
    ellas
    0.08
     bitte
    0.08
    Ø·Ùģ
    0.08
    quo
    0.08
    Activations Density 0.040%

    No Known Activations