© 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. 22-TRANSCODER-HP
    7. 88954
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     adequately
    -0.28
    åħħ足
    -0.27
     appropriately
    -0.26
     SHALL
    -0.25
     shall
    -0.25
    stral
    -0.25
    åįıè°ĥ
    -0.24
    æľ¬è´¨ä¸Ĭ
    -0.24
    NP
    -0.24
    åĽłåŃIJ
    -0.24
    POSITIVE LOGITS
    幸
    0.29
    çļĦ家åºŃ
    0.29
    äºĨåIJ§
    0.29
     parte
    0.28
    ĵį
    0.28
    çĶŁæ´»çļĦ
    0.26
    vented
    0.26
    gone
    0.25
     responsible
    0.25
    大家åĪĨ享
    0.25
    Activations Density 0.007%

    No Known Activations