© 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. 20-TRANSCODER-HP
    7. 129077
    Prev
    Next
    INDEX
    Explanations

    Brackets / code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ament
    -0.26
    alse
    -0.26
    andom
    -0.25
    ener
    -0.25
    .databinding
    -0.24
    Classes
    -0.24
    aman
    -0.24
    çīĩ
    -0.23
    isci
    -0.23
    lauf
    -0.23
    POSITIVE LOGITS
     kettle
    0.26
    岸边
    0.26
    opi
    0.25
    UGH
    0.24
    pher
    0.24
    ÑģÑĤаÑĤ
    0.24
    -kind
    0.24
     BDS
    0.24
    sass
    0.24
    æŃ¥éª¤
    0.23
    Activations Density 52.199%

    No Known Activations