© 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. 32-TRANSCODER-HP
    7. 40798
    Prev
    Next
    INDEX
    Explanations

    say "hyphen or ed ending"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Based
    -0.32
    based
    -0.31
    åŁºäºİ
    -0.30
    Based
    -0.29
     based
    -0.28
     freezes
    -0.26
     correlations
    -0.25
     partitions
    -0.25
    OMETRY
    -0.24
    ãĥŃãĥ¼
    -0.24
    POSITIVE LOGITS
    -driven
    0.35
    第ä¸Ģ
    0.35
    第ä¸Ģ个
    0.32
     first
    0.32
    -first
    0.32
    驱åĬ¨
    0.31
    First
    0.30
    led
    0.29
     First
    0.29
    rst
    0.29
    Activations Density 0.003%

    No Known Activations