© 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. 5167
    Prev
    Next
    INDEX
    Explanations

    spreadsheet formulas

    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
     intimate
    -0.27
    /jav
    -0.26
    å¹½
    -0.25
     gust
    -0.25
    etas
    -0.25
    cop
    -0.25
    tees
    -0.24
    å¯Ĩ
    -0.24
     hun
    -0.24
    kop
    -0.24
    POSITIVE LOGITS
    irty
    0.27
     Centers
    0.26
    Center
    0.25
    äºĶä¸Ģ
    0.25
    blind
    0.25
    ered
    0.25
     defaultCenter
    0.25
    acci
    0.24
    éĥĽ
    0.23
    å´´
    0.23
    Activations Density 0.103%

    No Known Activations