© 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. 8706
    Prev
    Next
    INDEX
    Explanations

    Return statements/code

    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
     qualified
    -0.27
    -derived
    -0.27
    .Automation
    -0.27
    ':{'
    -0.26
    uzu
    -0.26
    æĭ©
    -0.26
    qualified
    -0.25
     toReturn
    -0.25
    å¾Ĺåĩº
    -0.25
    tü
    -0.25
    POSITIVE LOGITS
    ARNING
    0.29
    æĹłè§Ĩ
    0.28
    ainless
    0.25
    .onView
    0.25
    ä¸įåıĹ
    0.24
    åħ¬å¼Ģ课
    0.24
    ision
    0.23
     اÙĦØŃاÙĦ
    0.23
    á»±c
    0.23
     broadcaster
    0.23
    Activations Density 0.042%

    No Known Activations