© 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. 6310
    Prev
    Next
    INDEX
    Explanations

    lens

    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
    oving
    -0.23
    æĮģå¹³
    -0.23
    åĴĮåľ°åĮº
    -0.23
    amped
    -0.23
    udio
    -0.22
     ↵            ↵
    -0.22
    erness
    -0.21
     WARRANTY
    -0.21
     ÑĥÑĩеб
    -0.21
     голоÑģ
    -0.21
    POSITIVE LOGITS
    less
    0.25
    ral
    0.24
    èĪ·
    0.24
    PM
    0.23
    æĹ¢çĦ¶
    0.23
    ä¸įæ¸ħ
    0.23
     deprived
    0.22
    (es
    0.22
    æŨ
    0.22
     própria
    0.22
    Activations Density 1.198%

    No Known Activations