© 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. 50338
    Prev
    Next
    INDEX
    Explanations

    suffix endings for words

    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
    g
    -0.08
     vs
    -0.06
    atta
    -0.06
    igh
    -0.06
    èµĬ
    -0.06
    ä¹Łå¯¹
    -0.06
    楼
    -0.05
    isch
    -0.05
    F
    -0.05
     &
    -0.05
    POSITIVE LOGITS
    lard
    0.08
    hev
    0.08
    serter
    0.08
    minos
    0.08
    ฯ
    0.08
     bersangkutan
    0.07
    -NLS
    0.07
    å¤įåĪ¶éĵ¾æİ¥
    0.07
    -BEGIN
    0.07
    alom
    0.07
    Activations Density 0.690%

    No Known Activations