© 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. 30-TRANSCODER-HP
    7. 95811
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curiosity
    -0.29
    erville
    -0.28
    æĸ¯å¡Ķ
    -0.26
    å¾Īæĸ¹ä¾¿
    -0.25
     Calder
    -0.25
    æĦī
    -0.25
    亲çĪ±
    -0.25
    cul
    -0.25
    ilog
    -0.24
    #index
    -0.24
    POSITIVE LOGITS
    éģ
    0.28
    è¡Ľ
    0.26
     objective
    0.26
    æĶ¯ä»ĺ
    0.26
    uard
    0.25
     tagging
    0.25
    åį«
    0.25
     bats
    0.25
    velt
    0.25
    iki
    0.24
    Activations Density 0.898%

    No Known Activations

    This feature has no known activations.