© 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. 12-TRANSCODER-HP
    7. 21956
    Prev
    Next
    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    bench
    -0.27
     bench
    -0.26
    -inverse
    -0.25
    å¼Ĥåľ°
    -0.24
    pon
    -0.24
    ih
    -0.24
    bij
    -0.24
     solid
    -0.24
    åı·åı¬
    -0.24
    ufact
    -0.23
    POSITIVE LOGITS
    tent
    0.29
    ,nil
    0.28
     slips
    0.27
    .times
    0.26
    Dao
    0.26
    硬度
    0.25
    Ahead
    0.25
    antly
    0.24
     suck
    0.24
    itemName
    0.24
    Activations Density 0.002%

    No Known Activations