© 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. 5433
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    _owned
    -0.27
    ä¹İ
    -0.27
    [msg
    -0.25
    -MM
    -0.24
     poisoned
    -0.24
    éĹ¾
    -0.24
    pei
    -0.24
    dition
    -0.23
    nowled
    -0.23
     glued
    -0.23
    POSITIVE LOGITS
    ental
    0.27
    stress
    0.24
    mons
    0.24
    墩
    0.24
    wy
    0.24
    ä¼łéĢģ
    0.23
    ind
    0.23
    åºĶåĬĽ
    0.23
    ilo
    0.23
    sted
    0.23
    Activations Density 0.036%

    No Known Activations