© 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. 27-TRANSCODER-HP
    7. 56322
    Prev
    Next
    INDEX
    Explanations

    Mi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     sidelines
    -0.27
    falls
    -0.26
     sail
    -0.26
     viral
    -0.25
    pu
    -0.25
    acent
    -0.24
    社ä¼ļåĮĸ
    -0.24
     Diss
    -0.24
    Sou
    -0.24
    mount
    -0.23
    POSITIVE LOGITS
    PIO
    0.29
    åĪ¶éĢłä¸ļ
    0.28
    éħª
    0.26
     acted
    0.26
     act
    0.25
    acts
    0.25
    äter
    0.24
    act
    0.23
    ä½ľçĶ¨
    0.23
     Scalars
    0.23
    Activations Density 1.025%

    No Known Activations