© 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. 6524
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
    è´¡
    -0.34
    éĻĨ
    -0.30
     Champ
    -0.26
    çļĦ人éĥ½
    -0.26
    éĻ¸
    -0.26
     Pars
    -0.25
     Donate
    -0.25
    always
    -0.24
    ponsible
    -0.24
     chatt
    -0.24
    POSITIVE LOGITS
    Âł
    0.26
     named
    0.26
    åIJį
    0.26
     name
    0.26
     Variant
    0.26
    æŃ£æĸĩ
    0.25
     åIJį
    0.25
     spl
    0.25
    sov
    0.25
    示
    0.24
    Activations Density 0.011%

    No Known Activations