© 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. 5756
    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
    èĹı
    -0.27
    çł´åĿı
    -0.26
    unting
    -0.26
    çĶ»çĶ»
    -0.26
    æ¦Ħ
    -0.26
     artistic
    -0.25
    æĮ¡ä½ı
    -0.25
    ugar
    -0.25
     Hurt
    -0.25
    æĹłè¾ľ
    -0.25
    POSITIVE LOGITS
     seekers
    0.26
    缴
    0.25
     last
    0.25
    last
    0.25
     dealers
    0.25
     barg
    0.25
    agy
    0.25
    å«ģ
    0.24
     geh
    0.24
    itous
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.