© 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. 107825
    Prev
    Next
    INDEX
    Explanations

    Medical/Scientific texts

    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
     deter
    -0.27
    =obj
    -0.27
    就说
    -0.26
    éĽĨä½ĵ
    -0.26
     Luca
    -0.26
    Highlight
    -0.25
    WARDS
    -0.25
    éĩįçĤ¹
    -0.25
    -lfs
    -0.24
    ÑĥлÑĮ
    -0.24
    POSITIVE LOGITS
    姣
    0.28
    ear
    0.26
    åį°
    0.26
    å¨ĩ
    0.26
    ufficient
    0.24
    izon
    0.24
     addCriterion
    0.23
     bread
    0.23
     picture
    0.23
    quier
    0.23
    Activations Density 6.409%

    No Known Activations