© 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. 9-TRANSCODER-HP
    7. 29373
    Prev
    Next
    INDEX
    Explanations

    Academic/technical writing snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    esti
    -0.26
    “My
    -0.26
    undi
    -0.26
     kata
    -0.25
    istica
    -0.24
     Führung
    -0.24
    theid
    -0.24
    âĢ¦”↵↵
    -0.24
     MutableList
    -0.24
    geries
    -0.23
    POSITIVE LOGITS
    åłĤ
    0.32
    æĽ¾
    0.30
     overnight
    0.30
     draining
    0.29
     unbiased
    0.27
     Encyclopedia
    0.27
    iven
    0.27
     unrecognized
    0.26
    åĽ°
    0.26
    èĢĥ
    0.26
    Activations Density 1.011%

    No Known Activations