© 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. 52644
    Prev
    Next
    INDEX
    Explanations

    Aliases or alternative names

    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
    åĴĮåħ¶ä»ĸ
    -0.94
    ä¸İåħ¶ä»ĸ
    -0.82
    æĪĸèĢħåħ¶ä»ĸ
    -0.72
    æĪĸåħ¶ä»ĸ
    -0.71
    åıĬåħ¶ä»ĸ
    -0.69
     Other
    -0.65
    (other
    -0.65
    以åıĬåħ¶ä»ĸ
    -0.64
    Other
    -0.59
    other
    -0.58
    POSITIVE LOGITS
    åĪ«
    1.48
    åĪ¥
    1.12
     alias
    0.71
     ali
    0.66
    alias
    0.65
     aliases
    0.61
    Alias
    0.60
    åĪ«è¯´
    0.59
    .alias
    0.58
    (alias
    0.58
    Activations Density 0.246%

    No Known Activations