© 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. 141384
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     Supplier
    -0.27
     transfers
    -0.23
     ne
    -0.23
    ök
    -0.23
    rupt
    -0.23
     Honour
    -0.23
     Formal
    -0.23
     Em
    -0.22
    ±Ð¾ÑĤ
    -0.22
    ";}↵
    -0.22
    POSITIVE LOGITS
    nist
    0.27
    antro
    0.27
    tti
    0.27
     corrid
    0.26
    å»Ĭ
    0.26
    满æĦıçļĦ
    0.25
    kowski
    0.25
    hdr
    0.25
    xit
    0.24
    arend
    0.24
    Activations Density 4.985%

    No Known Activations