© 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. 4797
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    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
    æĮij
    -0.31
    ETCH
    -0.25
    ⾧
    -0.25
    etAddress
    -0.25
    ately
    -0.24
    roduced
    -0.24
    ipelines
    -0.24
     tÃł
    -0.24
    -io
    -0.23
    ä¹Łç®Ĺ
    -0.23
    POSITIVE LOGITS
    å®ıè§Ĥ
    0.27
    icorn
    0.26
     heart
    0.25
     swollen
    0.25
     categor
    0.24
     hj
    0.24
    ixture
    0.24
    orias
    0.23
    yx
    0.23
    oxy
    0.23
    Activations Density 0.076%

    No Known Activations