© 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. 64497
    Prev
    Next
    INDEX
    Explanations

    Technical content

    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
    nt
    -0.29
    arendra
    -0.28
    ulan
    -0.27
    isphere
    -0.27
    å±ķ
    -0.25
     nan
    -0.25
    sid
    -0.25
    å¤ļä¹Ī
    -0.24
    rms
    -0.23
    unsubscribe
    -0.23
    POSITIVE LOGITS
    妹
    0.28
    绣
    0.27
    åħ¬ç¤¾
    0.27
    æ§Į
    0.25
    imony
    0.25
    omat
    0.25
    鹤
    0.24
    åĵģ
    0.24
    .cloudflare
    0.24
     revers
    0.24
    Activations Density 16.938%

    No Known Activations