© 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. 16945
    Prev
    Next
    INDEX
    Explanations

    arithmetic expressions

    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
    ẹn
    -0.08
    jenigen
    -0.08
     lẫn
    -0.08
    à¥įस
    -0.07
    æĥ¨æ·¡
    -0.07
     verste
    -0.07
    issi
    -0.07
    atteri
    -0.07
    OSE
    -0.07
    å°±æĢķ
    -0.07
    POSITIVE LOGITS
    loth
    0.07
    0.06
    eded
    0.06
    æŃ¢
    0.06
    ilon
    0.06
     hom
    0.06
    rm
    0.06
     superf
    0.05
    urd
    0.05
    æĿŁ
    0.05
    Activations Density 0.004%

    No Known Activations