© 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. 149228
    Prev
    Next
    INDEX
    Explanations

    Python code

    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
    aired
    -0.29
    urger
    -0.27
    è¿Ļ两
    -0.25
     shaft
    -0.25
    oft
    -0.24
     memoir
    -0.24
    -Men
    -0.24
     Correspond
    -0.24
    å°´å°¬
    -0.24
    .grid
    -0.23
    POSITIVE LOGITS
    溢
    0.30
    群éĩĮ
    0.28
    æ±Ģ
    0.26
     zun
    0.26
    izr
    0.25
    æķĽ
    0.25
    validate
    0.24
    CompleteListener
    0.24
    eous
    0.24
     clubs
    0.24
    Activations Density 0.157%

    No Known Activations