© 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. 31-TRANSCODER-HP
    7. 19704
    Prev
    Next
    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     rep
    -0.28
    rij
    -0.27
    ihan
    -0.26
     colonies
    -0.25
    inya
    -0.25
     Cater
    -0.25
    pj
    -0.25
    enga
    -0.25
    æłij
    -0.24
    综åIJĪæķ´æ²»
    -0.24
    POSITIVE LOGITS
    绿
    0.29
     limp
    0.29
    ä¸Ĭå¸Ĥ
    0.27
    etSocketAddress
    0.26
    apter
    0.26
    aceutical
    0.26
    .pick
    0.25
    æĶ¾è¿Ľ
    0.25
    åħīæ»ij
    0.25
    seealso
    0.25
    Activations Density 1.246%

    No Known Activations