© 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. 30-TRANSCODER-HP
    7. 95954
    Prev
    Next
    INDEX
    Explanations

    blood coagulation, medical events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩĿ
    -0.68
    è¡Ģ
    -0.61
     plate
    -0.57
    plate
    -0.56
    åĩĿèģļ
    -0.51
     Plate
    -0.50
     blood
    -0.49
    blood
    -0.48
    Blood
    -0.47
     clot
    -0.47
    POSITIVE LOGITS
    åĨ²
    0.24
    hattan
    0.24
     Ïĥ
    0.23
    vi
    0.23
    _sched
    0.23
     l
    0.23
     Tyson
    0.23
    窨
    0.23
     spirit
    0.22
    eria
    0.22
    Activations Density 0.944%

    No Known Activations