© 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. 33-TRANSCODER-HP
    7. 54797
    Prev
    Next
    INDEX
    Explanations

    Quantity/degree

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     few
    -0.48
     Few
    -0.34
    few
    -0.32
    å®ĥ
    -0.30
    Few
    -0.29
    å¼ķ
    -0.28
    /wiki
    -0.28
    å°ijæķ°
    -0.27
    åĩłä¸ªäºº
    -0.27
    ä¸ĭä¸Ģ个
    -0.26
    POSITIVE LOGITS
     less
    0.53
     a
    0.46
     Less
    0.40
     menos
    0.36
    Less
    0.35
     part
    0.35
     менее
    0.32
     weniger
    0.32
     indirectly
    0.31
    -less
    0.31
    Activations Density 0.058%

    No Known Activations