© 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. 62139
    Prev
    Next
    INDEX
    Explanations

    interior 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
    gebung
    -0.09
    à¯įà®ķ
    -0.09
    缸åħ³æ³ķå¾ĭ责任
    -0.09
    ionario
    -0.08
     osobowych
    -0.08
    eter
    -0.08
     demikian
    -0.08
    esian
    -0.08
    nable
    -0.08
    à¸Ľà¸£à¸°à¸Īำ
    -0.08
    POSITIVE LOGITS
    er
    0.18
    ly
    0.15
    ر
    0.12
    /ext
    0.11
    ÙĦ
    0.09
    most
    0.09
    erne
    0.09
    ance
    0.09
    mente
    0.09
    ment
    0.09
    Activations Density 0.018%

    No Known Activations