© 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. 141362
    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
    ength
    -0.27
    TÃľRK
    -0.26
    &o
    -0.24
    èģĶç³»æĸ¹å¼ı
    -0.24
    interaction
    -0.24
    designation
    -0.24
     encour
    -0.24
    eldom
    -0.23
    伺
    -0.23
    æľªç»ı
    -0.23
    POSITIVE LOGITS
     agent
    0.29
    çĬĦ
    0.28
     organ
    0.26
     root
    0.26
    queeze
    0.25
     (('
    0.25
    åĻľ
    0.25
     Sk
    0.24
     Bi
    0.24
     agents
    0.23
    Activations Density 17.428%

    No Known Activations

    This feature has no known activations.