© 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. 52531
    Prev
    Next
    INDEX
    Explanations

    technical documentation/code 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
    çĬģ
    -0.29
    -Am
    -0.29
    os
    -0.28
    oss
    -0.27
    OS
    -0.26
    -office
    -0.25
    åĨĽäºº
    -0.24
    agn
    -0.24
    æ·ĺæ±°
    -0.23
    æĭĽçīĮ
    -0.23
    POSITIVE LOGITS
    horn
    0.33
     roku
    0.29
    çĶ¥
    0.27
     cap
    0.27
    åĴĮæľįåĬ¡
    0.27
    äº
    0.26
    缯
    0.25
    å¾ģ
    0.25
    houses
    0.24
    housing
    0.24
    Activations Density 0.009%

    No Known Activations