© 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. 5028
    Prev
    Next
    INDEX
    Explanations

    Numbers and amounts

    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
     universally
    -0.29
    rias
    -0.28
    ARS
    -0.26
    æľį
    -0.24
    -scrollbar
    -0.24
     west
    -0.24
    aves
    -0.23
    ues
    -0.23
    æĺİçŁ¥
    -0.23
    ä»į
    -0.23
    POSITIVE LOGITS
    è¦ģç´§
    0.32
    åıĮéĩį
    0.29
    agit
    0.25
    esting
    0.25
    çļĦ家åºŃ
    0.25
     COPYRIGHT
    0.24
    çķĢ
    0.24
    ","",
    0.24
    )test
    0.24
    automatic
    0.24
    Activations Density 0.018%

    No Known Activations