© 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. 108500
    Prev
    Next
    INDEX
    Explanations

    ine

    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
    åijĬ
    -0.28
    mlink
    -0.26
    “
    -0.26
    “↵↵
    -0.25
    æĸĭ
    -0.25
     Affero
    -0.24
    ãĢģ“
    -0.24
    çĶľç¾İ
    -0.24
    andes
    -0.24
    ogl
    -0.24
    POSITIVE LOGITS
     total
    0.26
     ÑģобÑĢан
    0.24
    Quote
    0.24
     &=
    0.24
     leo
    0.24
     lúc
    0.23
    æĶ¾
    0.23
     intellectual
    0.23
     case
    0.23
    IZER
    0.23
    Activations Density 1.615%

    No Known Activations