© 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. 25-TRANSCODER-HP
    7. 109556
    Prev
    Next
    INDEX
    Explanations

    say the ending -ized

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rä
    -0.26
    -handed
    -0.26
     unanimous
    -0.26
     Trustees
    -0.26
    lm
    -0.26
    symbol
    -0.25
     Buckingham
    -0.25
    Nam
    -0.24
    ãĤĩãģĨ
    -0.24
    pte
    -0.24
    POSITIVE LOGITS
    anguard
    0.23
    ized
    0.23
    éķ¿å®ī
    0.23
    头çĹĽ
    0.23
    ÑĥÑĩ
    0.23
    å½ķ
    0.23
    (Spring
    0.23
    ÙĬØ©
    0.23
    omez
    0.23
    çij¶
    0.22
    Activations Density 0.165%

    No Known Activations