© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6583
    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
    culator
    -0.27
    æĮijæĪĺ
    -0.26
    è¿Łè¿Ł
    -0.26
    .construct
    -0.24
    _challenge
    -0.24
    å¿ħè¦ģãģĮãģĤãĤĬãģ¾ãģĻ
    -0.24
    ä»įæľª
    -0.24
    ardi
    -0.24
    _bases
    -0.24
    Encoded
    -0.23
    POSITIVE LOGITS
    å¾Ĺ天
    0.26
    iliated
    0.25
    änn
    0.25
    ysics
    0.24
     Recon
    0.24
    éĿĻéĿĻ
    0.24
     prey
    0.23
    -room
    0.23
    çŀŁ
    0.23
    éģ¥
    0.23
    Activations Density 0.989%

    No Known Activations

    This feature has no known activations.