© 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. 32-TRANSCODER-HP
    7. 43970
    Prev
    Next
    INDEX
    Explanations

    Mixed technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    vlc
    -0.28
    ocy
    -0.28
    åĴª
    -0.28
    adol
    -0.27
    ÑĩеÑĤ
    -0.27
    è´Ń票
    -0.27
    ILA
    -0.27
     panc
    -0.26
    acro
    -0.25
    nar
    -0.25
    POSITIVE LOGITS
    .cl
    0.27
    æĶ¾å¤§
    0.26
    eh
    0.25
     ih
    0.25
    åIJ
    0.24
    å®ģ
    0.24
    anged
    0.24
     Twe
    0.24
    fe
    0.23
     inf
    0.23
    Activations Density 0.000%

    No Known Activations