© 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. 40929
    Prev
    Next
    INDEX
    Explanations

    childhood abuse and health conditions

    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
    Ø©
    -0.09
    agle
    -0.08
    ative
    -0.08
    yle
    -0.07
    人æĿ¥è¯´
    -0.07
    edom
    -0.07
    onomy
    -0.07
    лÑĥÑĩ
    -0.07
    athon
    -0.07
    ãĤĪãģĨãģ«ãģªãĤĭ
    -0.07
    POSITIVE LOGITS
    à¥į
    0.10
    оÑĢоÑĤ
    0.08
    à§įড
    0.08
    mute
    0.08
    zinho
    0.08
    esign
    0.08
    ãĤ·ãĥĥãĥĹ
    0.08
    reens
    0.08
    ر
    0.07
    coder
    0.07
    Activations Density 0.011%

    No Known Activations