© 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. 5699
    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
     <
    -0.27
    onn
    -0.25
    onna
    -0.25
    **↵↵
    -0.24
    å¾Īä¹ħ
    -0.24
    ä¸ľè¥¿
    -0.24
    æĹ©
    -0.24
    å±ī
    -0.24
    chn
    -0.24
    **,
    -0.24
    POSITIVE LOGITS
    :host
    0.31
    èĢ»
    0.30
    _APB
    0.29
    ç»ŀ
    0.27
     elm
    0.25
     Kle
    0.24
     competitions
    0.23
    жд
    0.23
    éĢģ
    0.23
     Lore
    0.23
    Activations Density 0.972%

    No Known Activations

    This feature has no known activations.