© 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. 63947
    Prev
    Next
    INDEX
    Explanations

    scientific/technical documents

    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
    çħ§æł·
    -0.28
    èĩªèº«
    -0.25
    zilla
    -0.25
    çĭ
    -0.25
    äºİ
    -0.24
    ter
    -0.24
    åĥıæĺ¯
    -0.24
    —but
    -0.24
    äºĨä¸Ģ份
    -0.24
    åIJĦä½į
    -0.24
    POSITIVE LOGITS
    ¤í
    0.27
    otics
    0.25
    æŁ¥çľĭåħ¨æĸĩ
    0.24
    Bulk
    0.24
    åħ»
    0.24
     antiqu
    0.24
    acks
    0.23
    odate
    0.23
     outer
    0.23
     unt
    0.23
    Activations Density 28.479%

    No Known Activations