© 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. 6543
    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
    ount
    -0.27
     correspondence
    -0.26
    coe
    -0.26
    èģĮæĿĥ
    -0.26
    ous
    -0.25
    èģĮä¸ļ
    -0.25
    quam
    -0.25
    Equip
    -0.25
    ble
    -0.25
     secretary
    -0.25
    POSITIVE LOGITS
    /providers
    0.32
    åĬłå¼ºå¯¹
    0.26
     Gathering
    0.26
    tdown
    0.25
    å·¦åı³
    0.24
    èİł
    0.24
    creens
    0.23
    æĤ¬æµ®
    0.23
    åįģåĽĽæĿ¡
    0.23
    GroupId
    0.23
    Activations Density 0.550%

    No Known Activations

    This feature has no known activations.