© 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. 32-TRANSCODER-HP
    7. 41453
    Prev
    Next
    INDEX
    Explanations

    medical symptoms and diagnoses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cce
    -0.27
    çIJĨ论
    -0.27
    thesis
    -0.27
    ICY
    -0.27
    zung
    -0.27
     plung
    -0.26
    .safe
    -0.25
    issa
    -0.25
    DY
    -0.25
     theory
    -0.25
    POSITIVE LOGITS
     becoming
    0.37
     becomes
    0.33
     became
    0.31
    bec
    0.30
     become
    0.30
     nearest
    0.30
    æĪIJ为
    0.30
    æĪIJ为äºĨ
    0.30
    alon
    0.28
    ingleton
    0.28
    Activations Density 0.002%

    No Known Activations