© 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. 131070
    Prev
    Next
    INDEX
    Explanations

    letters and correlations

    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
    s
    -0.27
    éĢļ
    -0.26
    a
    -0.26
    å¸ĪèĮĥ
    -0.26
    è¯ī
    -0.26
    ä¸Ńä»ĭæľºæŀĦ
    -0.26
    unist
    -0.24
    inner
    -0.24
    een
    -0.24
     inner
    -0.24
    POSITIVE LOGITS
    PCS
    0.27
    dry
    0.25
     handleMessage
    0.25
    鬣
    0.24
    mailbox
    0.24
    ASF
    0.24
    currently
    0.24
    hdl
    0.24
    æķ´ä¸ªäºº
    0.23
     parch
    0.23
    Activations Density 51.730%

    No Known Activations