© 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. 6261
    Prev
    Next
    INDEX
    Explanations

    dust

    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
    åĴĮåľ°åĮº
    -0.28
    æĬĹ
    -0.26
    axe
    -0.26
    ddy
    -0.25
     sized
    -0.24
    antar
    -0.24
    ###↵
    -0.24
    act
    -0.23
    Mui
    -0.23
    axis
    -0.23
    POSITIVE LOGITS
    fulness
    0.31
    åĪ¸
    0.27
    åĬłå·¥
    0.27
    еÑĩно
    0.25
    åĬŀçIJĨ
    0.25
    naire
    0.24
    iero
    0.24
    ness
    0.23
    头ä¸Ĭ
    0.23
    好ä¸į容æĺĵ
    0.23
    Activations Density 2.312%

    No Known Activations