© 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. 18-TRANSCODER-HP
    7. 88221
    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_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    cka
    -0.27
     éc
    -0.26
    unk
    -0.25
    uctor
    -0.25
    ä¸įæĺİ
    -0.24
    NCY
    -0.24
    头
    -0.24
     tighter
    -0.24
    Äĩi
    -0.24
    ä¸ĭ车
    -0.23
    POSITIVE LOGITS
    åħ¨ãģ¦
    0.25
    uggest
    0.25
    è¿Ļä¸ĢåĪĩ
    0.25
    æŃĻ
    0.25
    æ²»
    0.25
    support
    0.24
    =-=-
    0.24
    CustomAttributes
    0.24
     recent
    0.24
    stretch
    0.24
    Activations Density 14.568%

    No Known Activations