© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    Manch Angeles

    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
    иÑĢа
    -0.07
    endorf
    -0.06
    ãĥĥãĤ¯ãĤ¹
    -0.06
    幸
    -0.06
    rac
    -0.06
    ekt
    -0.06
    estä
    -0.06
    SearchParams
    -0.06
    ofs
    -0.06
    lines
    -0.06
    POSITIVE LOGITS
    å·¥åķĨæĪ·
    0.09
    ï¾ŀ
    0.07
    gota
    0.07
     carto
    0.07
    æĭ§
    0.07
    insen
    0.07
    .mult
    0.07
     Westbrook
    0.07
    leo
    0.07
    icto
    0.07
    Activations Density 0.169%

    No Known Activations