© 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. 52751
    Prev
    Next
    INDEX
    Explanations

    Time after event

    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
    ¦Ĥ
    -0.29
     masc
    -0.28
    uess
    -0.27
    æĸ§
    -0.27
     requestOptions
    -0.26
    xsd
    -0.25
     Exclusive
    -0.25
    ltra
    -0.25
     mascot
    -0.25
    çIJĨè´¢
    -0.25
    POSITIVE LOGITS
     directly
    0.43
     ar
    0.36
     after
    0.34
     following
    0.33
     а
    0.33
    缴æİ¥
    0.32
     Ara
    0.32
     upon
    0.30
     ara
    0.30
     right
    0.30
    Activations Density 0.030%

    No Known Activations