© 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. 5809
    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
    åľ¨è¿ĩ渡
    -0.33
    pery
    -0.27
    åĪĿæŃ¥
    -0.24
     part
    -0.24
    :focus
    -0.24
    STANCE
    -0.24
    OfClass
    -0.24
    OLDER
    -0.23
     metav
    -0.22
     recal
    -0.22
    POSITIVE LOGITS
    æĸ¹ä¾¿
    0.27
    das
    0.27
    жа
    0.26
     Tra
    0.26
    еÑģÑĤв
    0.26
    deaux
    0.25
    rank
    0.25
    Tra
    0.24
    èıĮ
    0.24
    dn
    0.24
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.