© 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. 18-TRANSCODER-HP
    7. 88969
    Prev
    Next
    INDEX
    Explanations

    healthcare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anko
    -0.27
     tours
    -0.26
    FFE
    -0.26
     turb
    -0.26
    èĩªæĿ¥
    -0.25
    pps
    -0.25
    akis
    -0.25
    pipes
    -0.25
    åĸĦæĦı
    -0.24
     relu
    -0.23
    POSITIVE LOGITS
     surviving
    0.30
    å¥Ħ
    0.29
    heap
    0.27
    _caption
    0.27
    èī°
    0.26
     imminent
    0.26
    çĭ±
    0.25
    à¸Ħม
    0.25
     illness
    0.25
     dying
    0.24
    Activations Density 47.510%

    No Known Activations