© 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. 30-TRANSCODER-HP
    7. 95472
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çªģçł´åı£
    -0.27
    .statistics
    -0.26
    èĦ±é¢ĸ
    -0.26
    idency
    -0.25
    .Inject
    -0.25
    åĬ£
    -0.25
    éħ±æ²¹
    -0.24
    æł·åŃIJ
    -0.24
    -lg
    -0.24
    åħ¥åı£
    -0.24
    POSITIVE LOGITS
    æī¹
    0.27
    æļĤ
    0.27
    leep
    0.26
    åĢĮ
    0.26
    å¬ī
    0.26
     batch
    0.25
     Fat
    0.25
     вÑĢем
    0.25
     in
    0.25
    ,'"
    0.25
    Activations Density 0.099%

    No Known Activations

    This feature has no known activations.