© 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. 52582
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çī¹æĸ¯
    -0.28
     tensions
    -0.26
     Begin
    -0.26
     kindly
    -0.25
     absent
    -0.25
    çļĦçݰ象
    -0.25
     REF
    -0.25
     disap
    -0.25
     sugars
    -0.25
    çļĦæłĩåĩĨ
    -0.25
    POSITIVE LOGITS
    æĸ¹æ¡Ī
    0.32
    è¿ĩå¾Ĺ
    0.27
    /gl
    0.25
    akest
    0.25
    éĶ¦
    0.25
    åºı
    0.25
    BUM
    0.25
    afe
    0.25
     safest
    0.25
     eviction
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.