© 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. 63191
    Prev
    Next
    INDEX
    Explanations

    Codes and identifiers

    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
    scoped
    -0.30
     kilograms
    -0.26
    ä¸Ģ个éĹ®é¢ĺ
    -0.26
    (bs
    -0.25
    -inverse
    -0.24
    ä¸Ģ个å°ıæŶ
    -0.24
    Inverse
    -0.24
     Poison
    -0.24
    rary
    -0.23
     annotated
    -0.23
    POSITIVE LOGITS
    æĬĺ
    0.34
    endo
    0.27
    BAT
    0.27
    ç¢İçīĩ
    0.27
    大å¤ļ
    0.25
    å¹¼
    0.25
     luego
    0.25
    AB
    0.24
     fr
    0.24
    åŁºåĽł
    0.24
    Activations Density 32.976%

    No Known Activations