© 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. 9-TRANSCODER-HP
    7. 30475
    Prev
    Next
    INDEX
    Explanations

    arithmetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĭ±
    -0.27
    ping
    -0.25
    ãģİ
    -0.25
    é¼ĵ
    -0.24
    primitive
    -0.24
    ymb
    -0.24
     loạn
    -0.24
     bubble
    -0.24
    á»ĵn
    -0.24
    åijIJ
    -0.24
    POSITIVE LOGITS
    iVar
    0.28
    Tail
    0.27
    ï¼ģï¼ģ↵↵
    0.26
     Spreadsheet
    0.26
    .Invariant
    0.26
     histo
    0.25
    emarks
    0.25
    bred
    0.24
    ..."↵↵
    0.24
    Variant
    0.24
    Activations Density 5.379%

    No Known Activations