© 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. 129355
    Prev
    Next
    INDEX
    Explanations

    code 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
    第äºĮ个
    -0.25
    FFE
    -0.25
    æĶ¾è¿ĩ
    -0.24
    UGE
    -0.24
     oldest
    -0.24
     Interrupt
    -0.24
    éĹ®ä»ĸ
    -0.24
    第ä¸Ģ个
    -0.23
     directives
    -0.23
     orders
    -0.23
    POSITIVE LOGITS
    ersions
    0.29
    çļĦæĥħåĨµ
    0.28
    æ²ģ
    0.27
    ĥģ
    0.25
    plied
    0.25
    egral
    0.24
    nip
    0.24
    erce
    0.24
     Advertisement
    0.23
    optgroup
    0.23
    Activations Density 4.489%

    No Known Activations