© 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. 8680
    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
     apl
    -0.30
    å¹ķ
    -0.25
    é¢Ħå¤ĩ
    -0.25
    <th
    -0.24
    åĮħ袱
    -0.24
     concentrates
    -0.24
    an
    -0.24
    ç¹ģå¿Ļ
    -0.24
    Impl
    -0.24
    åĮ¿
    -0.24
    POSITIVE LOGITS
    å¿Ĺ
    0.29
    wit
    0.27
    lander
    0.26
    /sites
    0.25
    itta
    0.25
    icious
    0.25
    à¤Ŀ
    0.25
    Feat
    0.25
     Matte
    0.24
    åĪ«
    0.24
    Activations Density 0.812%

    No Known Activations

    This feature has no known activations.