© 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. 63261
    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
     fond
    -0.26
    olini
    -0.24
     Fond
    -0.24
    иж
    -0.24
    èĪįå¾Ĺ
    -0.23
    death
    -0.23
    admins
    -0.23
     [[[
    -0.23
    codec
    -0.23
    æīİ
    -0.22
    POSITIVE LOGITS
    侯
    0.26
     stage
    0.26
    ä»ĸæĺ¯
    0.25
    åħ«å¤§
    0.25
     Stage
    0.24
    ",@"
    0.24
    æĬ½
    0.24
    ä¸Ģæĺ¯
    0.24
    Stage
    0.23
    .jp
    0.23
    Activations Density 15.312%

    No Known Activations

    This feature has no known activations.