© 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. 52778
    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
     |\
    -0.29
    éĺ¶
    -0.28
     indeed
    -0.28
    ('.'
    -0.26
     Ze
    -0.26
    大æĸ¹
    -0.26
    槽
    -0.25
    |\
    -0.25
    orary
    -0.24
    çĺĹ
    -0.24
    POSITIVE LOGITS
    apter
    0.29
    çİ°å®ŀçĶŁæ´»
    0.28
     domina
    0.26
     privile
    0.26
    èĦ±é¢ĸèĢĮåĩº
    0.26
    tube
    0.26
     incomes
    0.25
     raining
    0.25
     getToken
    0.24
     Stre
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.