© 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. 5100
    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
    aab
    -0.27
    aud
    -0.27
     flatt
    -0.25
    uke
    -0.25
    åħ¥å¢ĥ
    -0.25
    çķĻæĦı
    -0.24
    xr
    -0.24
    olf
    -0.24
    æľĢåĪĿ
    -0.23
     finest
    -0.23
    POSITIVE LOGITS
    sez
    0.30
    åŃIJéĩĮ
    0.29
    uno
    0.27
    esse
    0.26
    osed
    0.25
    ständ
    0.25
     mix
    0.25
    sted
    0.25
    еÑģÑĤÑĮ
    0.24
    ÑĢож
    0.24
    Activations Density 2.254%

    No Known Activations

    This feature has no known activations.