© 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. 4866
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     profile
    -0.26
    .inc
    -0.25
    å¢Ļ
    -0.25
    mart
    -0.25
    诤
    -0.25
    ç§ķ
    -0.24
    projection
    -0.24
    æĪIJéķ¿ä¸º
    -0.24
    GetString
    -0.24
    abcdefghijklmnop
    -0.23
    POSITIVE LOGITS
    afari
    0.28
    plier
    0.25
    lei
    0.25
     poz
    0.24
    æ·¹
    0.24
    ä¸Ģå®ļä¼ļ
    0.24
     inter
    0.24
    бой
    0.24
    apo
    0.24
     res
    0.23
    Activations Density 0.079%

    No Known Activations

    This feature has no known activations.