© 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. 64857
    Prev
    Next
    INDEX
    Explanations

    Code/text 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
    Negative Logits
    redd
    -0.30
    red
    -0.28
     prof
    -0.28
    reds
    -0.28
    ım
    -0.26
    çĩĥ
    -0.26
    imm
    -0.26
     assumed
    -0.25
    <Post
    -0.25
    çĩĥæ°Ķ
    -0.25
    POSITIVE LOGITS
     Others
    0.30
    æľīåħ³è§Ħå®ļ
    0.29
    Others
    0.29
    åħ±åIJĮåĬªåĬĽ
    0.28
    åıijå±ķåīįæĻ¯
    0.28
     Moderate
    0.27
     hå
    0.27
    fds
    0.27
    ’.↵↵
    0.26
    udies
    0.26
    Activations Density 39.716%

    No Known Activations