© 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. 42821
    Prev
    Next
    INDEX
    Explanations

    all followed by nouns

    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
     vs
    -0.07
    åIJĪåIJĮæŶ
    -0.07
    uar
    -0.07
    åIJĦä½į
    -0.07
    keh
    -0.06
    大家
    -0.06
    kest
    -0.06
    ++.
    -0.06
    arf
    -0.06
    mic
    -0.06
    POSITIVE LOGITS
    owing
    0.09
    æĥħåĨµä¸ĭ
    0.09
    山头
    0.08
     dintre
    0.08
    —including
    0.08
    æĥħæ³ģä¸ĭ
    0.08
    undes
    0.08
    ä¹ĭåıĪ
    0.08
    ä¹ĭ以
    0.07
    ↵     ↵
    0.07
    Activations Density 0.121%

    No Known Activations