© 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
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 4862
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and identifiers

    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
     strang
    -0.28
    lems
    -0.28
     gam
    -0.27
    ility
    -0.27
    ilities
    -0.26
    acity
    -0.26
    à¸ªà¸łà¸²à¸ŀ
    -0.26
    bler
    -0.25
    uiten
    -0.25
     uncomfortable
    -0.24
    POSITIVE LOGITS
    横
    0.26
     AF
    0.25
     Videos
    0.25
    :X
    0.25
     unterstüt
    0.24
     videos
    0.24
     list
    0.24
     './../
    0.23
     ÑĢÑĥб
    0.23
     distract
    0.23
    Activations Density 0.027%

    No Known Activations