© 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. 4843
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     discounted
    -0.25
    иÑģк
    -0.25
     //↵↵
    -0.24
     discounts
    -0.24
    perf
    -0.23
    opsy
    -0.23
     Mesa
    -0.23
    NAL
    -0.23
    ZY
    -0.23
    -push
    -0.23
    POSITIVE LOGITS
     potential
    0.30
     direct
    0.30
    款
    0.29
    æĦıåij³
    0.28
    lim
    0.27
    _direct
    0.26
    OwnProperty
    0.26
    宵
    0.25
    -direct
    0.25
    æ½ľåľ¨
    0.25
    Activations Density 0.008%

    No Known Activations