© 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. 5223
    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
    uxt
    -0.26
    çī¹æľĹ
    -0.25
    ires
    -0.25
    çĹ£
    -0.25
    åĪĸ
    -0.25
    è§Ĵèī²
    -0.24
     мÑı
    -0.24
    è´¿
    -0.24
    èĥĮæĻ¯
    -0.23
    çĭ¸
    -0.23
    POSITIVE LOGITS
    erial
    0.30
    å¼ķèµ·äºĨ
    0.28
     upt
    0.27
    essional
    0.26
    æijĬ
    0.25
    pictures
    0.25
     Nap
    0.25
     pictures
    0.24
     CPS
    0.24
    æ¸ħæ´ģ
    0.24
    Activations Density 0.302%

    No Known Activations

    This feature has no known activations.