© 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. 5725
    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
    æ·±å¤Ħ
    -0.26
    ä¸įåĬ¨
    -0.26
    çļĦèīºæľ¯
    -0.25
    endar
    -0.25
    æİĸ
    -0.25
    èīºæľ¯
    -0.25
    ame
    -0.24
     bat
    -0.24
     mus
    -0.24
    ä¹ł
    -0.23
    POSITIVE LOGITS
    tas
    0.27
    anse
    0.27
    Att
    0.24
    广åijĬæľįåĬ¡
    0.24
    fine
    0.24
    æľī两个
    0.24
    woord
    0.24
    åº
    0.24
    cott
    0.23
    çĦ¦
    0.23
    Activations Density 0.605%

    No Known Activations

    This feature has no known activations.