© 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. 8348
    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
    ãģĤãĤĭ
    -0.28
    غا
    -0.28
    erty
    -0.28
    æŁIJç§į
    -0.27
    çļĦä¸Ģç§į
    -0.27
    æľīä¸Ģç§į
    -0.25
    bourg
    -0.25
    .newBuilder
    -0.25
    æĥħåĨµæĿ¥çľĭ
    -0.25
    第ä¸Ģå±Ĭ
    -0.25
    POSITIVE LOGITS
     sketch
    0.28
    çĻ¾
    0.27
     merit
    0.26
    poster
    0.26
    fried
    0.25
    èĶ¼
    0.25
    lobals
    0.25
    è¿ij
    0.24
    templates
    0.24
    ape
    0.24
    Activations Density 0.055%

    No Known Activations

    This feature has no known activations.