© 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. 27-TRANSCODER-HP
    7. 58621
    Prev
    Next
    INDEX
    Explanations

    robotic/robinson

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    unning
    -0.26
    atte
    -0.25
    é£Ł
    -0.23
     sis
    -0.22
    idas
    -0.22
     hon
    -0.22
     household
    -0.22
     mig
    -0.22
    太åŃIJ
    -0.22
    æĬ¤
    -0.22
    POSITIVE LOGITS
    bing
    0.29
    ä¸ĢåĪĢ
    0.28
    ics
    0.26
    ting
    0.26
    educt
    0.24
    technical
    0.24
    gram
    0.23
    æ¤Ĵ
    0.23
    duct
    0.23
    oth
    0.23
    Activations Density 0.096%

    No Known Activations