© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4966
    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
    æľīæŶ
    -0.28
    èĦIJ
    -0.27
    HING
    -0.26
    .nlm
    -0.25
    ANGO
    -0.25
    éĵ±
    -0.25
    ниÑİ
    -0.25
    车ä½į
    -0.25
    é¢ĦçķĻ
    -0.25
    theless
    -0.24
    POSITIVE LOGITS
    çŃīçĿĢ
    0.27
    onte
    0.26
    avis
    0.26
    cho
    0.24
     acquiring
    0.23
     Troll
    0.23
    arn
    0.22
    å¯Ŀ
    0.22
     Initialize
    0.22
    vince
    0.22
    Activations Density 0.038%

    No Known Activations

    This feature has no known activations.