© 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. 1058
    Prev
    Next
    INDEX
    Explanations

    placental birthweight ratio

    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
    交åĬŀ
    -0.08
    ania
    -0.07
    æ¦Ĥ念
    -0.07
    kong
    -0.07
    åºķåŃIJ
    -0.07
    empla
    -0.06
    åį³éĢĿ
    -0.06
    åĭ¿æī°
    -0.06
    unga
    -0.06
    _merged
    -0.06
    POSITIVE LOGITS
    鲨
    0.07
     disproportionately
    0.07
    asy
    0.07
    -fw
    0.07
    ngo
    0.07
    acc
    0.07
    Abb
    0.07
    asilan
    0.07
    aciente
    0.07
    -ob
    0.07
    Activations Density 0.016%

    No Known Activations