© 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. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19053
    Prev
    Next
    INDEX
    Explanations

    research reports about health

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dem
    -0.28
    NavController
    -0.27
    оÑģÑĤи
    -0.26
    æĸĭ
    -0.25
     Arg
    -0.25
    æľīåºı
    -0.25
    jal
    -0.24
    éĢļåħ³
    -0.24
    óst
    -0.24
    ön
    -0.24
    POSITIVE LOGITS
    æĬ¥åijĬ
    0.34
     report
    0.33
    lopen
    0.30
    -reported
    0.28
     trouble
    0.28
    kses
    0.27
    reports
    0.27
    report
    0.26
     Report
    0.26
     reports
    0.26
    Activations Density 0.224%

    No Known Activations