© 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. 108454
    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
    Not in Any Lists

    No Comments

    Negative Logits
    witch
    -0.28
    SPAN
    -0.28
     Wiki
    -0.27
    Wiki
    -0.26
     wiki
    -0.25
    à¹īว
    -0.25
    å¼Ģåħ³
    -0.25
    .googleapis
    -0.25
     Granny
    -0.25
    ORITY
    -0.24
    POSITIVE LOGITS
    .escape
    0.30
    åIJĥçļĦ
    0.28
    好åIJĥ
    0.28
    æ³ķå®Ŀ
    0.26
    ä¸įåıĹ
    0.26
    ä¸įæķ¢
    0.25
    çĪ¬
    0.25
    plates
    0.24
    ä¸įåĬ¨
    0.24
     неÑģк
    0.24
    Activations Density 3.324%

    No Known Activations

    This feature has no known activations.