© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2052
    Prev
    Next
    INDEX
    Explanations

    quantifier and noun combinations

    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
    zec
    -0.08
    ahan
    -0.06
    uus
    -0.06
    fo
    -0.06
    uvi
    -0.06
    aum
    -0.06
    è¡
    -0.06
     Ùħعد
    -0.06
    <|box_end|>
    -0.06
    为å¸Ī
    -0.06
    POSITIVE LOGITS
    çļĦ对象
    0.08
    ullo
    0.08
    assi
    0.08
    æģ¯çļĦ
    0.08
    lying
    0.07
    íľ´
    0.07
    大鱼
    0.07
    .timestamps
    0.07
    对象
    0.07
     nami
    0.07
    Activations Density 0.005%

    No Known Activations