© 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. 44229
    Prev
    Next
    INDEX
    Explanations

    say "to"

    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
    plevel
    -0.27
    ousy
    -0.26
    oks
    -0.25
    ä¸įè¦ģåĨį
    -0.24
    bright
    -0.24
    ports
    -0.24
     ocas
    -0.24
    奥æŀĹåĮ¹åħĭ
    -0.24
    ndata
    -0.24
     GOODMAN
    -0.23
    POSITIVE LOGITS
     To
    0.68
    åĪ°äºĨ
    0.65
     Towards
    0.65
    To
    0.63
    -to
    0.63
    _To
    0.63
    ToObject
    0.62
     unto
    0.61
     towards
    0.60
    èĩ³
    0.59
    Activations Density 0.001%

    No Known Activations