© 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. 22-TRANSCODER-HP
    7. 111034
    Prev
    Next
    INDEX
    Explanations

    Numbers and calculations

    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
    Negative Logits
    æįŁå¤±
    -0.29
    nal
    -0.27
    loss
    -0.27
     Loss
    -0.26
    DIC
    -0.26
     loss
    -0.26
    ç»´æĬ¤
    -0.25
    ãĤ¹ãĥļãĥ¼ãĤ¹
    -0.25
    Loss
    -0.25
    ál
    -0.25
    POSITIVE LOGITS
    FromDate
    0.27
     years
    0.26
     IDE
    0.26
    .Addr
    0.25
     little
    0.24
    åįģå¹´
    0.24
     setup
    0.24
     decades
    0.24
     Curse
    0.24
    çķĪ
    0.24
    Activations Density 0.002%

    No Known Activations