© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4724
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
    OOT
    -0.26
    举äºļ
    -0.25
    ddf
    -0.25
    潤
    -0.25
    ноÑģÑĤи
    -0.25
    ubs
    -0.25
    enal
    -0.24
     Äijâu
    -0.24
     }>
    -0.24
    Classes
    -0.24
    POSITIVE LOGITS
     hunters
    0.28
    -feed
    0.28
    vier
    0.25
    landers
    0.25
    achers
    0.25
     Curry
    0.24
     chore
    0.24
     cause
    0.24
     hunter
    0.23
    é©»
    0.23
    Activations Density 0.006%

    No Known Activations