© 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. 61381
    Prev
    Next
    INDEX
    Explanations

    checking for errors

    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
    ydd
    -0.10
    ä¸İ大
    -0.08
    ãģ»
    -0.08
    ayne
    -0.08
    çļĦ鼨
    -0.08
    æĿIJæĸĻåıĬ
    -0.07
    accio
    -0.07
    alit
    -0.07
    ì§ľ
    -0.07
    enner
    -0.07
    POSITIVE LOGITS
    å¥Īä½ķ
    0.08
    ult
    0.07
    æļĩ
    0.06
    Parsed
    0.06
    ange
    0.06
    åµĺ
    0.06
    untime
    0.06
    §
    0.06
    ä»ĬçĶŁ
    0.06
    °
    0.06
    Activations Density 0.008%

    No Known Activations