© 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. 62555
    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
     rather
    -0.29
    rather
    -0.28
    Gender
    -0.28
    EntryPoint
    -0.27
    æĦıå¢ĥ
    -0.25
    alia
    -0.25
     Aristotle
    -0.24
    Compat
    -0.24
    InstanceId
    -0.24
    æĢ§åĪ«
    -0.24
    POSITIVE LOGITS
    ä»ĭè´¨
    0.27
    еÑģÑĤÑĮ
    0.26
    ç»ı纪人
    0.26
    åIJ¬åIJ¬
    0.26
    -Ta
    0.25
     resolve
    0.25
    çŁ³å®¶
    0.25
    äºĶæľĪ
    0.25
    说æĺ¯
    0.24
    LEG
    0.24
    Activations Density 4.171%

    No Known Activations

    This feature has no known activations.