© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63471
    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
    eced
    -0.31
    ibal
    -0.28
    whel
    -0.28
    åĪĻ
    -0.28
    éŨ
    -0.26
    /ex
    -0.25
    æĺŃ
    -0.24
    çļĦäºĭ
    -0.24
    """.
    -0.24
    éŁ³
    -0.24
    POSITIVE LOGITS
    raf
    0.26
    jf
    0.25
     Ãģrea
    0.24
     ÐłÐ°
    0.24
    读æĩĤ
    0.23
    çľĭä¸įæĩĤ
    0.23
    æŃ£ãģĹãģĦ
    0.23
    .answers
    0.23
    å©ļ纱
    0.23
     Toolbar
    0.23
    Activations Density 4.177%

    No Known Activations

    This feature has no known activations.