© 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. 8466
    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
    èIJ¥
    -0.30
    åIJĦè¡ĮåIJĦ
    -0.27
    åħ·
    -0.26
    çĩŁ
    -0.25
    ya
    -0.25
    .za
    -0.24
     prospect
    -0.24
    æĿĤå¿Ĺ社
    -0.24
    sets
    -0.24
     Russia
    -0.23
    POSITIVE LOGITS
     kì
    0.33
    fers
    0.28
     Haram
    0.28
    quam
    0.27
     noqa
    0.27
    ãĥ¼ãĥ³
    0.26
    åıįå¼¹
    0.26
    erce
    0.26
     Äijẳng
    0.25
    åĴ³
    0.24
    Activations Density 0.114%

    No Known Activations

    This feature has no known activations.