© 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. 17965
    Prev
    Next
    INDEX
    Explanations

    physical laws and technical terms

    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
    æ¯Ķçħ§
    -0.07
    èİ·å¾Ĺè¶ħè¿ĩ
    -0.07
    AINS
    -0.07
    趣
    -0.07
    lai
    -0.06
    allis
    -0.06
     mills
    -0.06
    ASTE
    -0.06
    ÃģN
    -0.06
    elij
    -0.06
    POSITIVE LOGITS
    aco
    0.08
    воÑĢаÑĩ
    0.07
    左转
    0.07
    åı¥åı¥
    0.07
    curl
    0.07
    ãĥģãĥ©
    0.07
    ostal
    0.07
    .outer
    0.07
     Viale
    0.06
    ittest
    0.06
    Activations Density 0.001%

    No Known Activations