© 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. 88225
    Prev
    Next
    INDEX
    Explanations

    that

    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
    ,,,,,,,,
    -0.27
    kip
    -0.26
    å§IJ妹
    -0.26
    èĪį
    -0.24
    -head
    -0.24
    ä¹Łåıªæľī
    -0.24
     Filip
    -0.24
    èĨĺ
    -0.24
    ijke
    -0.24
    ERIC
    -0.24
    POSITIVE LOGITS
     blended
    0.29
     ".↵
    0.28
    inet
    0.28
    .instant
    0.25
     Levin
    0.24
     rebound
    0.24
    pany
    0.24
    itim
    0.24
    ä»Ģ
    0.24
    ä¼łå¯¼
    0.24
    Activations Density 8.527%

    No Known Activations