© 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. 20-TRANSCODER-HP
    7. 64486
    Prev
    Next
    INDEX
    Explanations

    science/medical research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĭĮ
    -0.27
     Mods
    -0.26
     furnishings
    -0.26
    berger
    -0.25
     attachments
    -0.24
    cepts
    -0.24
    å·ī
    -0.24
    ĵį
    -0.24
    umpy
    -0.24
    TERS
    -0.24
    POSITIVE LOGITS
    Ãłn
    0.25
     Äijá»Ļc
    0.25
    Reach
    0.25
    asString
    0.24
    Jones
    0.24
    .head
    0.24
    èIJ½åĪ°å®ŀå¤Ħ
    0.24
    å®Įåħ¨æ²¡æľī
    0.24
    overview
    0.23
    èĩ¼
    0.23
    Activations Density 8.273%

    No Known Activations