© 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. 62757
    Prev
    Next
    INDEX
    Explanations

    MD

    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
    mts
    -0.31
    è²Ĥ
    -0.28
    :last
    -0.26
    >About
    -0.26
    tti
    -0.25
     Info
    -0.24
    .yahoo
    -0.24
    mana
    -0.24
    Info
    -0.24
    ves
    -0.23
    POSITIVE LOGITS
    ALAR
    0.33
    iol
    0.30
    移åĪ°
    0.27
    满åĪĨ
    0.26
    estic
    0.26
    æĺ¯æĪij们
    0.26
    IAL
    0.26
    aty
    0.25
    aten
    0.25
    大楼
    0.25
    Activations Density 0.559%

    No Known Activations