© 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. 140657
    Prev
    Next
    INDEX
    Explanations

    to

    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
    æ¯Ķäºļ
    -0.31
     Wort
    -0.27
     PY
    -0.25
     disproportion
    -0.25
     ÑĢаÑģпÑĢоÑģÑĤÑĢанен
    -0.25
    orning
    -0.24
    åĦ¿
    -0.24
    orny
    -0.24
    ä¸Ģä¸ĭ
    -0.24
    çĶ·åŃ©
    -0.24
    POSITIVE LOGITS
    å°ĺ
    0.27
    reeze
    0.25
    alg
    0.25
    åIJĪçIJĨ
    0.24
    hind
    0.24
    achel
    0.24
    åĩĨ
    0.24
    assin
    0.24
     checkpoints
    0.24
    åĪĻ
    0.24
    Activations Density 12.782%

    No Known Activations