© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129901
    Prev
    Next
    INDEX
    Explanations

    research reproducibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     вал
    -0.26
    oli
    -0.25
    åĢ¾
    -0.25
    zähl
    -0.24
    ç¯ĩç«ł
    -0.23
     Hoff
    -0.23
    丧
    -0.23
     BindingFlags
    -0.23
     ama
    -0.23
    .define
    -0.23
    POSITIVE LOGITS
     replicate
    0.60
     reproduce
    0.55
     replic
    0.54
     repro
    0.52
     reprodu
    0.51
    éĩįçİ°
    0.50
     reproduced
    0.50
     reproduction
    0.50
     replication
    0.48
     replicated
    0.46
    Activations Density 0.026%

    No Known Activations