© 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. 9905
    Prev
    Next
    INDEX
    Explanations

    file extentions .txt

    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
    UGIN
    -0.07
    ações
    -0.07
    èĺĭ
    -0.07
    нÑĸка
    -0.07
    isle
    -0.07
    èĦ
    -0.07
    ëł¹
    -0.07
    ière
    -0.06
    agem
    -0.06
    ãs
    -0.06
    POSITIVE LOGITS
    âĸł
    0.10
    èĮĥæĸĩç½ij
    0.08
    ",'
    0.07
    ãĢģãĢģ
    0.07
    ].'
    0.07
    ãĢĤï¼Į
    0.07
    å¿Ĺ强
    0.07
    ensen
    0.07
    amble
    0.07
    ).'
    0.07
    Activations Density 0.168%

    No Known Activations