© 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. 63964
    Prev
    Next
    INDEX
    Explanations

    Raw materials and agriculture

    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
    quee
    -0.30
    Tester
    -0.27
     Tester
    -0.27
    oting
    -0.26
    HING
    -0.26
    uzzle
    -0.25
     tours
    -0.25
     onCreateViewHolder
    -0.25
    ÑĪив
    -0.25
    inged
    -0.24
    POSITIVE LOGITS
    å¦Ī
    0.26
    åºĨ
    0.26
    æĪĪ
    0.25
    çģ¿çĥĤ
    0.25
    dd
    0.25
    |^
    0.24
    techn
    0.24
     mistaken
    0.24
    ervo
    0.24
    ék
    0.23
    Activations Density 13.240%

    No Known Activations