© 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. 12-TRANSCODER-HP
    7. 22024
    Prev
    Next
    INDEX
    Explanations

    Spring, flowers, growth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     commitment
    -0.30
     commit
    -0.27
    çī¢
    -0.26
    åı¯éĿł
    -0.26
    妥
    -0.26
    earn
    -0.25
    éĢĤ
    -0.25
    /il
    -0.25
     latest
    -0.25
     committing
    -0.24
    POSITIVE LOGITS
    éģĤ
    0.27
    iali
    0.27
    пÑĥ
    0.27
     desn
    0.26
    -offs
    0.26
    wagon
    0.26
    izens
    0.25
    è¡°
    0.25
    lds
    0.24
    onaut
    0.24
    Activations Density 0.000%

    No Known Activations