© 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. 5281
    Prev
    Next
    INDEX
    Explanations

    Coding and wildlife

    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
    aroo
    -0.30
    rias
    -0.28
    illas
    -0.28
    éªĸ
    -0.28
    nik
    -0.25
    åħģ
    -0.25
    ãģķãģĽ
    -0.25
    ãģ¾ãģĦ
    -0.24
     nigeria
    -0.24
    éĥ½åĸľæ¬¢
    -0.24
    POSITIVE LOGITS
    主åĬĽ
    0.29
    主åĬĽåĨĽ
    0.24
    /MIT
    0.24
    avo
    0.24
    AND
    0.23
    findViewById
    0.23
     karÅŁ
    0.23
     Ter
    0.23
    èķ
    0.23
     Calder
    0.23
    Activations Density 0.082%

    No Known Activations