© 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. 64675
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
    以为
    -0.31
    æĪij以为
    -0.29
     invention
    -0.26
    以çĤº
    -0.26
     nextPage
    -0.24
    çļĦåİĭåĬĽ
    -0.24
     er
    -0.24
     liked
    -0.24
    iction
    -0.23
    æĺ¶
    -0.23
    POSITIVE LOGITS
    ç¦ıåĪ©
    0.27
    olv
    0.26
    寡
    0.26
    tent
    0.26
    iting
    0.26
     Marg
    0.25
    oser
    0.25
    iom
    0.25
    caff
    0.25
    å§ĭ
    0.25
    Activations Density 1.321%

    No Known Activations