© 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. 20-TRANSCODER-HP
    7. 128976
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ervas
    -0.28
    åīŁ
    -0.26
    erval
    -0.25
    çĨŁ
    -0.25
    Union
    -0.24
    èµ·çĤ¹
    -0.24
     satur
    -0.24
    æ¶ĪèĢĹ
    -0.24
     Union
    -0.23
    .interval
    -0.23
    POSITIVE LOGITS
    ::-
    0.26
    ARNING
    0.26
    á»ģu
    0.25
    PerPixel
    0.25
    bows
    0.24
    ç³Ĺ
    0.24
     bleiben
    0.24
    -hand
    0.24
    使çĶ¨çļĦ
    0.24
     Kenneth
    0.23
    Activations Density 18.143%

    No Known Activations

    This feature has no known activations.