© 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. 58398
    Prev
    Next
    INDEX
    Explanations

    Arrests and legal issues

    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
    usable
    -0.27
     functional
    -0.26
    èĪĴ
    -0.25
    rica
    -0.25
     penetr
    -0.25
    ria
    -0.25
    ocup
    -0.25
    xca
    -0.25
     personal
    -0.24
    rio
    -0.24
    POSITIVE LOGITS
    gence
    0.34
    ä¸Ģ头
    0.29
    ation
    0.27
    æļ´åĬĽ
    0.27
    ction
    0.26
    å¾Ļ
    0.26
    FromArray
    0.26
     cheated
    0.25
    (UUID
    0.25
    å¥Ħ
    0.25
    Activations Density 0.003%

    No Known Activations