© 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. 142131
    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
    使åĬ²
    -0.25
    ມ
    -0.25
    auty
    -0.24
     outbound
    -0.24
    aks
    -0.24
    æĬ¥ä¸ļ
    -0.24
     eag
    -0.24
     centroids
    -0.23
     russian
    -0.23
    along
    -0.23
    POSITIVE LOGITS
    ItemAt
    0.29
    ç»ĨåĪĨ
    0.27
    羣æŃ£
    0.27
    ocked
    0.26
    è¿ĻäºĽéĹ®é¢ĺ
    0.25
    erver
    0.25
    è¿Ļ个éĹ®é¢ĺ
    0.24
     CONF
    0.24
    确认
    0.24
    onn
    0.24
    Activations Density 1.374%

    No Known Activations

    This feature has no known activations.