© 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. 30-TRANSCODER-HP
    7. 97028
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/technical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     fallen
    -0.26
    å¸ĤåľºåĮĸ
    -0.26
    çħ§æł·
    -0.25
    etary
    -0.25
    IJľ
    -0.25
    __.__
    -0.25
    rames
    -0.25
     incur
    -0.24
     pac
    -0.24
    DOWN
    -0.24
    POSITIVE LOGITS
    Connell
    0.28
    olders
    0.27
    ijing
    0.27
    å¸IJ篷
    0.26
     Processes
    0.26
    .Parser
    0.25
    ject
    0.24
    mutable
    0.24
    ì¹ĺ
    0.24
    iller
    0.23
    Activations Density 0.886%

    No Known Activations