© 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. 62562
    Prev
    Next
    INDEX
    Explanations

    publications and questions

    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
    äºĶåįĥ
    -0.27
     Conte
    -0.25
    ÃŃcio
    -0.24
    lain
    -0.24
    anova
    -0.24
     Again
    -0.23
    nnen
    -0.23
    beck
    -0.23
     Ðijа
    -0.23
    malink
    -0.23
    POSITIVE LOGITS
    æĶ¾åľ¨
    0.27
    ?)↵
    0.26
    )?$
    0.26
    ä¸Ģè´¯
    0.26
    ç½®äºİ
    0.25
    eto
    0.25
    :");č↵
    0.24
    iet
    0.24
    çŃĶçĸij
    0.24
    (gen
    0.24
    Activations Density 5.864%

    No Known Activations