© 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. 5160
    Prev
    Next
    INDEX
    Explanations

    initials

    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
    tright
    -0.26
    åĬłçĽĸ
    -0.26
     Staples
    -0.26
    rett
    -0.25
    heels
    -0.25
    éģ¿
    -0.24
    åĩºåħ¥
    -0.24
     crashing
    -0.23
    mtree
    -0.23
    è´§è¿IJ
    -0.23
    POSITIVE LOGITS
    escription
    0.26
    æ¢Ń
    0.25
    åĪº
    0.25
    Claims
    0.25
    elight
    0.24
    ç¼ĸç»ĩ
    0.24
    arcy
    0.24
     mentions
    0.23
    æĪIJåĬŁçļĦ
    0.23
    å½Ĵ纳
    0.23
    Activations Density 0.033%

    No Known Activations