© 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. 130899
    Prev
    Next
    INDEX
    Explanations

    question

    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
    人éĥ½
    -0.28
     NOR
    -0.27
     sins
    -0.27
    åĩºéŨ
    -0.26
    æ´ĭ
    -0.26
    commission
    -0.26
     оÑģнове
    -0.26
    èĤ¼
    -0.26
    .dot
    -0.25
    +offset
    -0.25
    POSITIVE LOGITS
    æľ¬èº«å°±
    0.25
    åIJĪä¸Ģ
    0.25
    raft
    0.25
    ality
    0.25
    ãĥ¯ãĥ¼ãĤ¯
    0.25
    ÑĤики
    0.25
    æľ¬èº«çļĦ
    0.24
    ator
    0.24
     myself
    0.24
    CHK
    0.24
    Activations Density 9.799%

    No Known Activations