© 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. 48226
    Prev
    Next
    INDEX
    Explanations

    following the word "once"

    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
    sWith
    -0.11
    jenigen
    -0.09
    ings
    -0.08
    onnen
    -0.08
    беÑĢа
    -0.07
    shire
    -0.07
    swith
    -0.07
    aschen
    -0.07
    ìŀIJ격
    -0.07
     vá»±c
    -0.07
    POSITIVE LOGITS
    /if
    0.12
    maal
    0.10
    enna
    0.09
    쯤
    0.09
    Ùĭ
    0.08
    رة
    0.08
    人
    0.08
    çĦ¶æĺ¯
    0.08
    -ever
    0.08
    à¦ĩ
    0.08
    Activations Density 0.040%

    No Known Activations