© 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. 61693
    Prev
    Next
    INDEX
    Explanations

    adi/ad/ropic/str/man with suffixes

    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
    riture
    -0.08
    Ł
    -0.07
    prim
    -0.07
    имеÑĢ
    -0.07
    redo
    -0.07
    igth
    -0.07
     paie
    -0.07
    orten
    -0.07
    æ±Łè·¯
    -0.07
    åĴĮå¤ĦçIJĨ
    -0.07
    POSITIVE LOGITS
    ity
    0.09
    arahan
    0.07
    ой
    0.07
     Hath
    0.07
    Ø©
    0.07
    ogen
    0.07
    antee
    0.07
    licity
    0.07
    entication
    0.07
    ÑĥÑģа
    0.07
    Activations Density 0.001%

    No Known Activations