© 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. 5414
    Prev
    Next
    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    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
    åŃ¦æľŁ
    -0.26
    åĵĻ
    -0.25
    çªģåıij
    -0.24
    opia
    -0.24
     Builds
    -0.24
    åľ®
    -0.24
    åĬ¨çĶŁæĪIJ
    -0.24
    persist
    -0.23
    ibi
    -0.23
    RAFT
    -0.23
    POSITIVE LOGITS
    éĤ£ä¹Īç®Ģåįķ
    0.26
    egral
    0.26
    ØŃ
    0.25
     Extend
    0.24
     ext
    0.24
    åı¹æģ¯
    0.24
     bound
    0.24
    åĢŁçĶ¨
    0.24
    æĬ±
    0.23
    зв
    0.23
    Activations Density 0.020%

    No Known Activations