© 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. 40545
    Prev
    Next
    INDEX
    Explanations

    Code, symbols

    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
     amount
    -0.26
    çļĦåĽłç´ł
    -0.26
     ifs
    -0.26
    æĹı
    -0.25
    %M
    -0.25
    æī©
    -0.25
     miá»ģn
    -0.24
    好è¯Ħ
    -0.24
    çļĦä¼Łå¤§
    -0.24
    .magnitude
    -0.23
    POSITIVE LOGITS
    án
    0.27
    æŶåĪ»
    0.27
    ante
    0.26
    aad
    0.26
    anel
    0.26
    onna
    0.26
     hidden
    0.25
     spotlight
    0.25
    onium
    0.24
    aud
    0.24
    Activations Density 0.204%

    No Known Activations