© 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. 58370
    Prev
    Next
    INDEX
    Explanations

    ending with -ations, -ings, etc

    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
     sü
    -0.24
    ç³Ł
    -0.24
     vie
    -0.24
    è¯Ħè®®
    -0.24
     Wed
    -0.24
    åįİ丽
    -0.24
    currentIndex
    -0.24
     Dis
    -0.23
     Mel
    -0.23
     Respond
    -0.23
    POSITIVE LOGITS
    ations
    0.36
    ages
    0.34
    ements
    0.33
    ients
    0.31
    ings
    0.30
    itions
    0.30
    atement
    0.30
    ering
    0.30
    AGER
    0.29
    uation
    0.29
    Activations Density 0.004%

    No Known Activations