© 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. 4945
    Prev
    Next
    INDEX
    Explanations

    Processes

    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
    åı°
    -0.31
    Åį
    -0.29
    ges
    -0.28
    ahu
    -0.28
    è¹Ļ
    -0.28
    座è°Īä¼ļä¸Ĭ
    -0.26
    èĩº
    -0.25
     sla
    -0.25
    Ash
    -0.25
    _commands
    -0.24
    POSITIVE LOGITS
    ViewItem
    0.28
    acie
    0.27
    æĪĨ
    0.25
    /+
    0.24
    burgh
    0.24
    ä¸įåIJĥ
    0.24
    =item
    0.24
    isArray
    0.24
    estre
    0.23
    æľīä¸Ģ天
    0.23
    Activations Density 0.058%

    No Known Activations