© 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. 62977
    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
    æļĸæ°Ķ
    -0.35
     xsi
    -0.30
    éħİ
    -0.26
    ordon
    -0.25
    ther
    -0.25
     Peel
    -0.24
     Nu
    -0.24
    è½®å»ĵ
    -0.24
    饺åŃIJ
    -0.24
    çĶļèĩ³
    -0.24
    POSITIVE LOGITS
    åĪĨ彩
    0.28
    ram
    0.26
     Emerging
    0.26
    æĸ°çļĦä¸Ģå¹´
    0.26
    æŃĮ
    0.26
    赦
    0.25
    éħ¬
    0.24
     dist
    0.24
    rawer
    0.24
    ozo
    0.23
    Activations Density 0.679%

    No Known Activations

    This feature has no known activations.