© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9514
    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
    Negative Logits
    æĭ¿æĿ¥
    -0.28
    èijŃ
    -0.27
    ä¸Ģå®ļ
    -0.26
    ë°°
    -0.25
    æķ£
    -0.25
    GRES
    -0.24
    å·¥ä¸ļ
    -0.24
    Sdk
    -0.24
    nr
    -0.24
    ç¼ĵåĨ²
    -0.24
    POSITIVE LOGITS
    ä¸ĭä¸Ģ
    0.29
    ä¸ĭä¸Ģ个
    0.29
    -next
    0.26
    AILS
    0.25
    çŃĶåį·
    0.25
    èµĥ
    0.25
    ith
    0.24
    illy
    0.24
    ails
    0.24
    otics
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.