© 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. 5405
    Prev
    Next
    INDEX
    Explanations

    account

    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
    dden
    -0.23
    mond
    -0.23
    inkle
    -0.23
     Memorial
    -0.22
    éĽ³
    -0.22
    isman
    -0.22
     Gins
    -0.22
    ениÑı
    -0.22
    _bitmap
    -0.21
    und
    -0.21
    POSITIVE LOGITS
    ician
    0.25
    gage
    0.25
    ees
    0.24
    sWith
    0.23
    manship
    0.23
     ReturnType
    0.23
    NotFoundError
    0.23
     cé
    0.22
    book
    0.22
    mates
    0.22
    Activations Density 0.947%

    No Known Activations