© 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. 35-TRANSCODER-HP
    7. 38573
    Prev
    Next
    INDEX
    Explanations

    c

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    z
    -0.35
    cc
    -0.34
    irc
    -0.33
    er
    -0.33
    ia
    -0.32
    ccc
    -0.32
    abal
    -0.32
    ular
    -0.31
    arp
    -0.31
    еп
    -0.31
    POSITIVE LOGITS
    et
    0.26
     Numerous
    0.26
    åIJİèĢħ
    0.23
    bish
    0.22
    åģķ
    0.22
     numerous
    0.22
    wg
    0.22
    etu
    0.22
    ä¸įå°ij
    0.22
     latter
    0.21
    Activations Density 83.558%

    No Known Activations