© 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. 7899
    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
    åı¯è°ĵ
    -0.31
    åı¯ä»¥è¯´æĺ¯
    -0.29
    -0.26
    ä¸Ģ代
    -0.26
    ç¥ŀç§ĺ
    -0.25
    æĺ¯ä¸Ģ件
    -0.25
    etc
    -0.25
    ä¸Ģ大åłĨ
    -0.25
     judging
    -0.24
    红æĹĹ
    -0.24
    POSITIVE LOGITS
    eping
    0.27
    gaard
    0.27
    .hp
    0.26
     penet
    0.25
    ulle
    0.25
    focus
    0.24
     Lia
    0.24
     mest
    0.24
    uvre
    0.24
    UNET
    0.24
    Activations Density 0.205%

    No Known Activations

    This feature has no known activations.