© 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. 27-TRANSCODER-HP
    7. 56394
    Prev
    Next
    INDEX
    Explanations

    Oxygen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .ind
    -0.31
    ilda
    -0.28
    nis
    -0.28
     digest
    -0.27
    æĸIJ
    -0.27
    ç£
    -0.27
    è¡Įä¸ļåĨħ
    -0.26
     IND
    -0.26
    çİīçŁ³
    -0.25
    -ind
    -0.25
    POSITIVE LOGITS
     Oxygen
    0.39
    æ°§
    0.36
     oxygen
    0.35
     captures
    0.27
    æīĴ
    0.26
     oxide
    0.25
    .getObject
    0.25
     capture
    0.25
    ijľ
    0.25
    capture
    0.25
    Activations Density 0.005%

    No Known Activations