© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5294
    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
    lit
    -0.28
    IOR
    -0.26
    hung
    -0.26
    $log
    -0.25
    myModal
    -0.25
     chóng
    -0.24
    intent
    -0.24
    eam
    -0.24
    åĬŁçİĩ
    -0.24
    åĽ°éļ¾
    -0.23
    POSITIVE LOGITS
    åij¼åı«
    0.27
    AUSE
    0.27
    ASE
    0.27
    çİ©èĢį
    0.25
     statusCode
    0.25
    è°ĵ
    0.25
    alar
    0.25
    clide
    0.24
    USTER
    0.24
    æłĩ注
    0.24
    Activations Density 0.138%

    No Known Activations

    This feature has no known activations.