© 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. 52726
    Prev
    Next
    INDEX
    Explanations

    sm

    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
     cont
    -0.30
    ãĥ©ãĤ¤ãĥ³
    -0.26
    wner
    -0.26
    æĬĬ她
    -0.26
     ours
    -0.25
    cade
    -0.25
    opic
    -0.25
     anonymity
    -0.24
     yours
    -0.24
    cont
    -0.24
    POSITIVE LOGITS
    ysical
    0.29
    å§ľ
    0.27
    jax
    0.26
    èªĵ
    0.26
    elize
    0.26
    AAP
    0.26
     Airways
    0.25
    æĬ¥åIJį
    0.25
    ActionCreators
    0.25
    amping
    0.24
    Activations Density 0.011%

    No Known Activations