© 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. 31-TRANSCODER-HP
    7. 17970
    Prev
    Next
    INDEX
    Explanations

    career

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     dro
    -0.28
     dropping
    -0.27
     useStyles
    -0.26
    /if
    -0.26
     Hearts
    -0.25
     keyof
    -0.25
    und
    -0.25
     unhealthy
    -0.24
    une
    -0.24
    urga
    -0.24
    POSITIVE LOGITS
    æ»ŀåIJİ
    0.27
    ваÑĤ
    0.26
    aar
    0.26
    Delimiter
    0.26
    Separator
    0.25
    åħĪæĬĬ
    0.25
    æľīä¸Ģä½į
    0.25
    -marker
    0.25
    æľīä¸Ģ个
    0.25
    CLA
    0.25
    Activations Density 0.144%

    No Known Activations