© 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. 63375
    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
    请éĹ®
    -0.26
    éŸ
    -0.24
    å½¼
    -0.24
    æį¢æĪIJ
    -0.23
    çīĩåĪ»
    -0.23
    anyl
    -0.23
    ecycle
    -0.23
    å¾Ĵ
    -0.23
    .ones
    -0.23
    udit
    -0.22
    POSITIVE LOGITS
    east
    0.28
     McMahon
    0.27
     Demp
    0.26
    .Serializable
    0.25
    plen
    0.25
     }}}
    0.25
    è¿Ļ个æĹ¶ä»£
    0.24
     HCI
    0.24
     VM
    0.24
    åį»
    0.24
    Activations Density 8.327%

    No Known Activations

    This feature has no known activations.