© 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. 33-TRANSCODER-HP
    7. 53542
    Prev
    Next
    INDEX
    Explanations

    medical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rão
    -0.31
     Chatt
    -0.28
    å®ħ
    -0.28
    adius
    -0.27
    icides
    -0.27
    unds
    -0.27
    istence
    -0.26
    á»ģn
    -0.26
    conomy
    -0.26
    reon
    -0.25
    POSITIVE LOGITS
     contributor
    0.35
     exporter
    0.34
     emitter
    0.34
    imizer
    0.32
     defender
    0.32
     conductor
    0.31
     examiner
    0.31
     executor
    0.31
     producer
    0.31
     researcher
    0.31
    Activations Density 0.037%

    No Known Activations