© 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. 52769
    Prev
    Next
    INDEX
    Explanations

    code

    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
    FEATURE
    -0.42
     features
    -0.37
    feature
    -0.36
    /features
    -0.36
     Features
    -0.36
     FEATURE
    -0.36
    Features
    -0.34
    features
    -0.34
     feature
    -0.32
     FEATURES
    -0.31
    POSITIVE LOGITS
    umont
    0.28
     IQueryable
    0.27
    /light
    0.25
     peel
    0.25
    åħīçݯ
    0.25
     stret
    0.24
     intra
    0.24
    aml
    0.24
    :init
    0.24
    åĮħ
    0.24
    Activations Density 0.019%

    No Known Activations