© 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. 8018
    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
    éģĦ
    -0.28
    .Immutable
    -0.26
    è¾Ł
    -0.26
    åıĺå¼Ĥ
    -0.24
    omens
    -0.24
    ä¸Ģ缴æĺ¯
    -0.24
    ä¿Ŀåį«
    -0.24
    esModule
    -0.24
    ERVED
    -0.24
    evin
    -0.23
    POSITIVE LOGITS
    å¢ĥçķĮ
    0.27
    uche
    0.26
    MAT
    0.25
    æĢĢçĿĢ
    0.25
     tá»Ń
    0.24
    ä¸Ģ人
    0.24
    æģ©
    0.24
    çĩķ
    0.24
    ä¸Ģäºĭ
    0.24
    utt
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.