© 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. 142466
    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
    EN
    -0.27
    é½IJ
    -0.26
    éĺIJéĩĬ
    -0.25
    WB
    -0.24
     fail
    -0.24
    éĺħ读
    -0.24
    è¯ī
    -0.24
    ramer
    -0.23
    SEL
    -0.23
     comunic
    -0.23
    POSITIVE LOGITS
    length
    0.25
    å¹´ä¹ĭä¹ħ
    0.24
    |r
    0.24
    èī¯å¿ĥ
    0.24
    intValue
    0.24
    ('.'
    0.23
    ativas
    0.23
     GRAT
    0.23
     matrimon
    0.23
    å¾Īæ¼Ĥ亮
    0.23
    Activations Density 2.874%

    No Known Activations

    This feature has no known activations.