© 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. 9544
    Prev
    Next
    INDEX
    Explanations

    Coherent English text

    np_max-act · gemini-2.0-flash
    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
    /renderer
    -0.27
     shortcuts
    -0.25
    pest
    -0.24
    åĿł
    -0.24
    [string
    -0.23
    're
    -0.23
     dragon
    -0.23
    zar
    -0.23
     Shortcut
    -0.23
    çĶ»å®¶
    -0.23
    POSITIVE LOGITS
    çİĩ为
    0.31
     airs
    0.24
     PURE
    0.24
     promise
    0.23
    NER
    0.23
     Tel
    0.23
    Including
    0.23
    Cycle
    0.23
    CLUSIVE
    0.22
    amt
    0.22
    Activations Density 0.522%

    No Known Activations