© 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. 33-TRANSCODER-HP
    7. 54631
    Prev
    Next
    INDEX
    Explanations

    Machine-generated text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ités
    -0.29
    åĴ¤
    -0.26
    楷
    -0.26
     w
    -0.25
    ::
    -0.25
    컬
    -0.24
    :w
    -0.24
    .Horizontal
    -0.23
     Minh
    -0.23
    Template
    -0.23
    POSITIVE LOGITS
    lian
    0.28
    cen
    0.28
    è³¢
    0.28
    iec
    0.27
    çĴĺ
    0.26
    гÑĢамм
    0.26
    Bear
    0.26
    ä¸įæ¸ħæ¥ļ
    0.24
    çĥŃéĩı
    0.24
    ãģĿãĤĮãģ«
    0.24
    Activations Density 0.012%

    No Known Activations