© 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. 19-TRANSCODER-HP
    7. 8734
    Prev
    Next
    INDEX
    Explanations

    Months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CID
    -0.27
    ucer
    -0.27
    etz
    -0.26
     grate
    -0.25
    ITES
    -0.25
    å¯Ĩ
    -0.25
     donating
    -0.24
    å¿ĥæĥħ
    -0.24
     {}:
    -0.23
    åĵģè´¨
    -0.23
    POSITIVE LOGITS
     Organ
    0.25
    åĨķ
    0.25
     hog
    0.24
     Knock
    0.24
    affen
    0.24
     Due
    0.24
     dia
    0.24
    {'
    0.23
    åĽºåĮĸ
    0.23
    åĩĨ
    0.23
    Activations Density 0.001%

    No Known Activations