© 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. 6508
    Prev
    Next
    INDEX
    Explanations

    dangerous

    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
    farm
    -0.26
     Newly
    -0.24
    lvl
    -0.23
     succeeding
    -0.23
     Structure
    -0.23
    tos
    -0.23
    çij¾
    -0.23
    Ñijн
    -0.23
     Various
    -0.22
    çī¢
    -0.22
    POSITIVE LOGITS
    thy
    0.27
    riend
    0.25
    人éĥ½
    0.25
     enough
    0.25
    askan
    0.24
     overst
    0.24
    -ish
    0.24
     heritage
    0.23
    than
    0.23
     Ames
    0.23
    Activations Density 0.756%

    No Known Activations