© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7070
    Prev
    Next
    INDEX
    Explanations

    is are

    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
     Guerr
    -0.28
    quarters
    -0.27
    åıĪ被
    -0.25
    eur
    -0.24
     hors
    -0.24
     quarters
    -0.24
    rell
    -0.23
    Ars
    -0.23
    (kernel
    -0.23
     WARRANTY
    -0.23
    POSITIVE LOGITS
    letal
    0.28
    alen
    0.27
    ä¸į说
    0.25
    ceptors
    0.25
    ego
    0.25
    ={({
    0.24
    丰åİļ
    0.23
    æĪijåı¯ä»¥
    0.23
    plug
    0.23
    endregion
    0.23
    Activations Density 0.890%

    No Known Activations