© 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. 22-TRANSCODER-HP
    7. 88075
    Prev
    Next
    INDEX
    Explanations

    medical events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼Łå¤§çļĦ
    -0.29
    ä¼Łå¤§
    -0.28
    creens
    -0.28
    oti
    -0.27
    å¥
    -0.27
    creen
    -0.26
    æŁ¥çľĭ详æĥħ
    -0.26
    era
    -0.25
    mixed
    -0.25
    -screen
    -0.25
    POSITIVE LOGITS
     uncompressed
    0.28
    èĩ¾
    0.26
    Radi
    0.26
     wiped
    0.25
     sang
    0.23
    "Well
    0.23
    .bed
    0.23
    æķ£åıij
    0.23
     dotyczÄħce
    0.22
    .gr
    0.22
    Activations Density 0.003%

    No Known Activations