© 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. 7327
    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
    æij½
    -0.28
    çĶļèĩ³æĺ¯
    -0.28
    vh
    -0.27
    elsen
    -0.26
     anyway
    -0.26
    åĮħ
    -0.25
    fort
    -0.25
    ivism
    -0.24
    ä¼łç»Łäº§ä¸ļ
    -0.24
    åĿļåĽº
    -0.24
    POSITIVE LOGITS
     Tamb
    0.26
    бед
    0.25
     review
    0.25
    æ®´
    0.25
    å·®å¼Ĥ
    0.25
     Cá»Ļng
    0.24
    å®ļäºĨ
    0.24
    åıijèµ·
    0.24
     kvp
    0.24
     Fabric
    0.23
    Activations Density 0.106%

    No Known Activations

    This feature has no known activations.