© 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. 18-TRANSCODER-HP
    7. 90334
    Prev
    Next
    INDEX
    Explanations

    final, last

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Applied
    -0.28
    .configure
    -0.27
     gehören
    -0.26
    PerPixel
    -0.26
    аÑĨион
    -0.25
    brown
    -0.25
    edList
    -0.25
    edImage
    -0.25
     Cum
    -0.24
     Leads
    -0.24
    POSITIVE LOGITS
     currently
    0.30
    expo
    0.27
     sortable
    0.27
     professions
    0.26
    æľĢ好
    0.25
    ä»¿ä½Ľ
    0.25
    ä¸īåĪĨä¹ĭä¸Ģ
    0.24
    estar
    0.24
     metro
    0.24
    andin
    0.24
    Activations Density 1.912%

    No Known Activations