© 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. 141181
    Prev
    Next
    INDEX
    Explanations

    Article text snippets

    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
    继ç»Ń
    -0.31
    ä¾Ŀæŧ
    -0.29
    isco
    -0.28
    adden
    -0.28
    iss
    -0.28
     continued
    -0.27
    äºĨä¸Ģ份
    -0.27
    ä¾ĿçĦ¶
    -0.27
    æĺ¯å¦Ĥä½ķ
    -0.26
    ä»įæŧ
    -0.26
    POSITIVE LOGITS
     divert
    0.27
    -dom
    0.26
    lide
    0.25
    ongs
    0.25
     dom
    0.24
     pall
    0.24
    itta
    0.24
    çIJ¶
    0.23
     keynote
    0.23
    èµ·çłģ
    0.23
    Activations Density 15.606%

    No Known Activations