© 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. 44126
    Prev
    Next
    INDEX
    Explanations

    say "to" word

    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
     even
    -0.43
    çĶļèĩ³
    -0.40
     даже
    -0.39
    åĪ°
    -0.39
    -to
    -0.38
     Even
    -0.38
    Even
    -0.37
    ToObject
    -0.36
    åĪ°äºĨ
    -0.35
    even
    -0.35
    POSITIVE LOGITS
    ookie
    0.29
    æľīæľŁ
    0.26
    ä¸ºæľŁ
    0.26
    饱
    0.25
    asper
    0.25
    pong
    0.24
     way
    0.24
    åIJĮä»ģ
    0.24
    åħ¼ä»»
    0.24
    rone
    0.24
    Activations Density 0.006%

    No Known Activations