© 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. 24-TRANSCODER-HP
    7. 151431
    Prev
    Next
    INDEX
    Explanations

    preparing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Stam
    -0.26
    å¡«
    -0.24
    éĺľ
    -0.24
    ä¸įå¿į
    -0.24
    çĬ¯
    -0.24
    oved
    -0.24
    eña
    -0.23
    enis
    -0.23
    controlled
    -0.23
    ä¸įå°½
    -0.23
    POSITIVE LOGITS
    åĩĨå¤ĩ
    0.85
     prepare
    0.76
    åĩĨå¤ĩ好
    0.75
     prepared
    0.74
     preparation
    0.69
    prepare
    0.68
     Prepare
    0.68
     preparations
    0.67
    .prepare
    0.64
     prepares
    0.64
    Activations Density 0.992%

    No Known Activations