© 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. 52670
    Prev
    Next
    INDEX
    Explanations

    ind

    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
    TRA
    -0.30
    atan
    -0.30
    æĬķ票
    -0.27
     rude
    -0.27
     atan
    -0.25
     unc
    -0.25
    æľªå©ļ
    -0.24
    syn
    -0.24
    roma
    -0.24
     Synthetic
    -0.24
    POSITIVE LOGITS
    ulg
    0.31
    ifference
    0.31
    ul
    0.29
    ignite
    0.29
    igs
    0.26
    cing
    0.26
     eruption
    0.26
    uls
    0.26
    ussels
    0.25
    uly
    0.25
    Activations Density 0.022%

    No Known Activations