© 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. 63133
    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
    аÑĢа
    -0.28
    pher
    -0.28
     Am
    -0.26
    à¹Ħล
    -0.26
     locally
    -0.26
    è½®
    -0.26
     slur
    -0.25
    ç©Ĩ
    -0.25
    ely
    -0.25
    ç´«
    -0.24
    POSITIVE LOGITS
     withStyles
    0.29
    ä¾Ľå¤§å®¶
    0.26
     midd
    0.26
    .openConnection
    0.26
    affles
    0.26
    addAction
    0.25
    çĶ¨æĪ·æıIJä¾Ľ
    0.25
     Braun
    0.25
     Sadd
    0.24
    .unknown
    0.24
    Activations Density 1.080%

    No Known Activations

    This feature has no known activations.