© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129901
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .Persistent
    -0.25
    åѤåĦ¿
    -0.25
     incest
    -0.25
     Pure
    -0.25
    ableView
    -0.24
    jsc
    -0.24
    夸
    -0.24
    ç§ĥ
    -0.24
    夫å¦ĩ
    -0.23
    ä»Ģä¹Īéĥ½ä¸į
    -0.23
    POSITIVE LOGITS
    ä¾Ľ
    0.29
    ivism
    0.27
    äº
    0.27
    忽
    0.25
    ä¸Ģ个人
    0.25
     Dodge
    0.24
    å°įæĸ¹
    0.24
    TD
    0.24
    arkan
    0.24
     Bá»Ļ
    0.24
    Activations Density 1.284%

    No Known Activations

    This feature has no known activations.