© 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. 24-TRANSCODER-HP
    7. 151343
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pair
    -0.31
     list
    -0.27
    pairs
    -0.27
    pair
    -0.26
    .list
    -0.25
    list
    -0.25
    lix
    -0.24
    é¦ĸä½į
    -0.24
     candidate
    -0.24
    Languages
    -0.24
    POSITIVE LOGITS
    éĩįå¤į
    0.33
     Copies
    0.33
     batches
    0.31
    =batch
    0.29
    copies
    0.28
     copies
    0.28
    æī¹éĩı
    0.28
     repeating
    0.27
    樣
    0.27
    è¡Ĺä¸Ĭ
    0.27
    Activations Density 1.023%

    No Known Activations