© 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. 129775
    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
    itten
    -0.28
    gett
    -0.27
     Poison
    -0.26
    esson
    -0.26
     pony
    -0.26
     POV
    -0.26
    åı£è¢ĭ
    -0.25
     Wass
    -0.25
    Pocket
    -0.25
    ä»»æĦı
    -0.24
    POSITIVE LOGITS
    游æĪıéĩĮçļĦ
    0.27
     interrog
    0.27
    (jq
    0.26
    好å¥ĩå¿ĥ
    0.26
    robe
    0.25
    楸
    0.24
    -pre
    0.23
     interrogation
    0.23
    涮
    0.23
    æ¢ħèĬ±
    0.23
    Activations Density 65.134%

    No Known Activations

    This feature has no known activations.