© 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. 19839
    Prev
    Next
    INDEX
    Explanations

    now!

    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
    δο
    -0.08
    оÑģÑĤи
    -0.07
    essel
    -0.07
    ÂŃ
    -0.07
    VL
    -0.06
    çħ©
    -0.06
    βε
    -0.06
    äºīå½ĵ
    -0.06
    δÏĮ
    -0.06
    ä»Ģä¹Īä¸ľè¥¿
    -0.06
    POSITIVE LOGITS
    è°´
    0.08
    adá
    0.07
    IER
    0.07
    æĪİ
    0.07
    aken
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
    å¢ĥ
    0.06
    asury
    0.06
    alli
    0.06
    è²Ķ
    0.06
    Activations Density 0.067%

    No Known Activations