© 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. 7779
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸İåıijå±ķ
    -0.29
    åIJ¯
    -0.27
    åĴĮåıijå±ķ
    -0.26
     Addresses
    -0.25
    们çļĦ
    -0.25
    jt
    -0.25
    —for
    -0.25
    åĴĮå®ĮåĸĦ
    -0.25
    ock
    -0.24
    -inc
    -0.24
    POSITIVE LOGITS
    uant
    0.29
    serie
    0.26
    ä¸įè´Ł
    0.25
    æĸ°éĹ»åıijå¸ĥ
    0.25
    æŀģéĢŁ
    0.25
    lane
    0.24
    å¹´åºķ
    0.24
    mise
    0.24
     paycheck
    0.24
    ÙĬا
    0.24
    Activations Density 1.093%

    No Known Activations

    This feature has no known activations.