© 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. 6307
    Prev
    Next
    INDEX
    Explanations

    text formatting and annotations

    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
    velle
    -0.26
     hosp
    -0.25
    .Utility
    -0.25
    主管
    -0.24
     Sanctuary
    -0.24
    eldon
    -0.24
    .hxx
    -0.23
     hass
    -0.23
    -proof
    -0.23
    çļĦåģļæ³ķ
    -0.23
    POSITIVE LOGITS
    éĩijèī²
    0.32
    æłĩ注
    0.31
    æľīèī²
    0.31
    é»Ħèī²
    0.30
    marked
    0.30
    ç²īèī²
    0.30
     colored
    0.30
     marked
    0.30
    åī§ä¸Ń
    0.28
     shaded
    0.28
    Activations Density 0.080%

    No Known Activations