© 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. 107044
    Prev
    Next
    INDEX
    Explanations

    in

    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
    /cop
    -0.30
    mans
    -0.30
    éĽĨåĽ¢èĤ¡ä»½
    -0.27
     condemned
    -0.27
    âĺ°
    -0.26
     condemn
    -0.25
    è°®
    -0.25
     condem
    -0.25
    orthand
    -0.25
     ?><
    -0.24
    POSITIVE LOGITS
    “
    0.29
    isis
    0.26
    isa
    0.26
    串
    0.25
    isi
    0.25
    tem
    0.25
     |
    0.25
     /
    0.25
    isu
    0.25
    l
    0.25
    Activations Density 8.927%

    No Known Activations