© 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. 54719
    Prev
    Next
    INDEX
    Explanations

    Gene sequence encoding

    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
     all
    -0.31
    gel
    -0.30
    çIJĨåıij
    -0.28
    all
    -0.28
     mor
    -0.28
     cann
    -0.28
    aram
    -0.27
    ss
    -0.27
     ure
    -0.27
    èĥ¶
    -0.27
    POSITIVE LOGITS
     codes
    0.50
    代çłģ
    0.47
     Codes
    0.47
     Code
    0.46
     code
    0.45
    codes
    0.45
    Code
    0.43
    ody
    0.43
    (Code
    0.43
    ãĤ³ãĥ¼ãĥī
    0.43
    Activations Density 0.015%

    No Known Activations