© 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. 129431
    Prev
    Next
    INDEX
    Explanations

    Technical or academic discussion

    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
    ç±¼
    -0.28
    spiel
    -0.27
     userModel
    -0.26
    dbuf
    -0.26
     UserModel
    -0.26
    对åºĶ
    -0.25
     UserController
    -0.25
    \Helper
    -0.25
    usher
    -0.25
     userList
    -0.25
    POSITIVE LOGITS
    å¯Ĥå¯ŀ
    0.29
    便
    0.25
     itself
    0.25
     tens
    0.25
    åѤçĭ¬
    0.24
    注
    0.24
    rys
    0.24
    åĸĦ
    0.24
    s
    0.23
     others
    0.23
    Activations Density 13.886%

    No Known Activations