© 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. 142095
    Prev
    Next
    INDEX
    Explanations

    lifetime

    np_max-act · gemini-2.0-flash
    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
     similarly
    -0.28
    åħ¥é©»
    -0.27
    é¾ĻéŨ
    -0.26
     notably
    -0.26
    åŃĺ款
    -0.25
    æŃ£å¥½
    -0.25
    itti
    -0.25
    çĭĻåĩ»
    -0.25
    notes
    -0.24
    åħ¥ãĤĬ
    -0.24
    POSITIVE LOGITS
    ä¾Ŀ
    0.26
     bunch
    0.25
    ç²Ĵ
    0.25
    uddy
    0.25
    -des
    0.24
    '],['
    0.24
    advertisement
    0.23
    _scheme
    0.23
     sunshine
    0.23
     continu
    0.23
    Activations Density 7.477%

    No Known Activations