© 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. 33-TRANSCODER-HP
    7. 54838
    Prev
    Next
    INDEX
    Explanations

    say "'s word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    s
    -0.50
    们
    -0.34
    们çļĦ
    -0.33
    顾
    -0.26
    arel
    -0.25
    `s
    -0.24
    éĺ¿
    -0.24
    åĮºåĨħ
    -0.24
    转
    -0.23
    æĶ»
    -0.23
    POSITIVE LOGITS
    ä»Ģä¹Īéĥ½
    0.27
    大è¡Ĺ
    0.27
    ãģ®ãģ§
    0.25
    homes
    0.25
     Sachs
    0.24
    天èĬ±
    0.24
    Inset
    0.23
    acus
    0.23
    Silver
    0.23
     Sink
    0.23
    Activations Density 0.018%

    No Known Activations