© 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. 44241
    Prev
    Next
    INDEX
    Explanations

    pattern prediction

    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
     ad
    -0.29
    æĶ¾å¤§
    -0.29
     amplify
    -0.29
     ap
    -0.28
    /--
    -0.28
    ulkan
    -0.27
    ArgsConstructor
    -0.27
    {{{
    -0.25
     amplified
    -0.25
     magn
    -0.25
    POSITIVE LOGITS
     patter
    0.32
    pattern
    0.29
    um
    0.28
    æľīæĦı
    0.28
    prediction
    0.27
    NP
    0.27
    ä½İä¼°
    0.26
    ippo
    0.26
    hits
    0.25
    ÑĢÑĥÑĤ
    0.25
    Activations Density 0.001%

    No Known Activations