© 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. 6331
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    FormItem
    -0.27
    ultipartFile
    -0.27
    ffective
    -0.27
    ainted
    -0.26
    plist
    -0.26
    èĻļæŀĦ
    -0.26
    ivable
    -0.25
     UUID
    -0.25
    ĸī
    -0.25
    anst
    -0.25
    POSITIVE LOGITS
    fra
    0.26
    casting
    0.26
    cast
    0.26
    å¾Ģ
    0.26
    tridge
    0.26
    st
    0.26
    å®Ŀ
    0.25
    æģ¢
    0.25
     Similar
    0.25
     similar
    0.25
    Activations Density 0.019%

    No Known Activations