© 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. 6004
    Prev
    Next
    INDEX
    Explanations

    Code and numerical data

    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
    ductive
    -0.27
    BN
    -0.25
    Naz
    -0.24
    etadata
    -0.23
     szczegóÅĤowo
    -0.23
     fixing
    -0.23
    aidu
    -0.23
    æľ¬ç½ij
    -0.23
    ä¸Ĭåİ»
    -0.23
    ardware
    -0.23
    POSITIVE LOGITS
     anything
    0.26
    inge
    0.25
     anyone
    0.25
     anybody
    0.25
    anything
    0.24
     пÑĢедÑĥÑģмоÑĤÑĢен
    0.24
    izu
    0.24
     chops
    0.24
    encing
    0.23
     kidd
    0.23
    Activations Density 0.038%

    No Known Activations