© 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. 90056
    Prev
    Next
    INDEX
    Explanations

    Completeness

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ç°¿
    -0.29
    ocks
    -0.27
    cors
    -0.26
    åķ¬
    -0.26
    ategory
    -0.26
    主管
    -0.25
    flater
    -0.24
    <source
    -0.24
    orer
    -0.23
    zos
    -0.23
    POSITIVE LOGITS
    oplan
    0.30
     stable
    0.26
     desc
    0.25
    ä¿©
    0.25
     conclusion
    0.24
     Treasurer
    0.24
     –
    0.24
     descend
    0.24
    æĺ¯æľĢ好çļĦ
    0.24
     dict
    0.24
    Activations Density 20.149%

    No Known Activations