© 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. 5719
    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
     LJ
    -0.26
     backward
    -0.26
    backward
    -0.25
    èĥ½åģļåĪ°
    -0.25
    atatype
    -0.25
     Spice
    -0.25
     terme
    -0.24
     métier
    -0.24
    èµ°ä¸ĭåİ»
    -0.24
    ä¼łæĦŁ
    -0.24
    POSITIVE LOGITS
    erved
    0.27
    é¦
    0.26
    aver
    0.25
    æ¸ħæĺİ
    0.25
    Plot
    0.25
    ile
    0.25
    ä½Ļ
    0.24
     explained
    0.24
     momentarily
    0.24
    in
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.