© 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. 20-TRANSCODER-HP
    7. 131051
    Prev
    Next
    INDEX
    Explanations

    entering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iquer
    -0.27
    due
    -0.27
     Każdy
    -0.27
    æĪ¶
    -0.27
    reduce
    -0.25
     advance
    -0.25
    计
    -0.25
     hunt
    -0.25
     due
    -0.25
    imdi
    -0.25
    POSITIVE LOGITS
    nbr
    0.27
    峡
    0.26
    çļĦåħ³ç³»
    0.26
    ToPoint
    0.25
    å®Ļ
    0.25
    pired
    0.24
    éĶ²
    0.24
    à¸ŀา
    0.24
     >",
    0.24
     erf
    0.24
    Activations Density 15.036%

    No Known Activations