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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5853
    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
    äºĮ线
    -0.28
    å°±æĺ¯ä¸ºäºĨ
    -0.26
    åıªè¦ģæľī
    -0.26
     Hp
    -0.26
    å°Ķæĸ¯
    -0.26
    hid
    -0.25
     bour
    -0.25
     coverage
    -0.25
     writ
    -0.25
     hg
    -0.25
    POSITIVE LOGITS
     tennis
    0.27
    rael
    0.27
    ãĥ»
    0.25
    ports
    0.25
    ricular
    0.25
    ::↵
    0.24
     patents
    0.24
    âĢ¢↵↵
    0.23
    TER
    0.23
    ãĢİ
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.