© 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. 61216
    Prev
    Next
    INDEX
    Explanations

    explaining why or how

    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
    ados
    -0.08
    iform
    -0.07
    ä¸įåĪĨ
    -0.07
    ader
    -0.07
    egger
    -0.07
    etypes
    -0.06
    träg
    -0.06
     '_',
    -0.06
    é¹ĥ
    -0.06
    é²ľèī³
    -0.06
    POSITIVE LOGITS
    issi
    0.08
    :\\
    0.08
     daarbij
    0.07
    angs
    0.07
    δι
    0.07
     antaranya
    0.07
    å¬
    0.07
    çıij
    0.07
    akest
    0.07
    wy
    0.07
    Activations Density 0.020%

    No Known Activations