© 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. 52516
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
    人éĹ´
    -0.27
    _pod
    -0.26
     Everyday
    -0.26
    deo
    -0.25
    Expose
    -0.24
    _than
    -0.23
    duk
    -0.23
    佯
    -0.23
    de
    -0.23
     unzip
    -0.23
    POSITIVE LOGITS
    atura
    0.28
    -S
    0.28
    eric
    0.27
    说æĺİ书
    0.27
    åı¥è¯Ŀ
    0.26
    .bits
    0.25
    âĦī
    0.25
    æĿ¥çĶµ
    0.25
    -ST
    0.25
    SS
    0.25
    Activations Density 0.004%

    No Known Activations