© 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. 4774
    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
    ä¹ĭéģĵ
    -0.29
     tog
    -0.28
    大å®ĹåķĨåĵģ
    -0.27
    auté
    -0.26
    æĭ©
    -0.26
    çĥŃçĤ¹
    -0.25
    å·§å¦Ļ
    -0.25
    æģŃ
    -0.25
    æ°Ķæģ¯
    -0.25
    çŃī级
    -0.25
    POSITIVE LOGITS
    ially
    0.36
    oria
    0.27
    -chief
    0.26
     MSR
    0.26
    %x
    0.26
    æĪĸå¤ļ
    0.25
     innocent
    0.25
     stylist
    0.25
    Stretch
    0.24
    wró
    0.24
    Activations Density 0.050%

    No Known Activations

    This feature has no known activations.