© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 140823
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Negative Logits
     Baghd
    -0.25
    æѦ
    -0.24
     offence
    -0.24
    ä¸įæŃ¢
    -0.24
    èĢģ大
    -0.24
     duke
    -0.24
     Bounty
    -0.24
    å¾µ
    -0.24
    wers
    -0.24
    #error
    -0.24
    POSITIVE LOGITS
    éĢĤæŶ
    0.28
    ient
    0.28
    eka
    0.26
    awa
    0.26
    æŃ¥
    0.26
     season
    0.26
     Steps
    0.26
    ìłĪ
    0.26
    ANDOM
    0.25
     Desired
    0.24
    Activations Density 3.226%

    No Known Activations