© 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. 33-TRANSCODER-HP
    7. 53560
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨ä»ĸçļĦ
    -0.31
    åľ¨ä»ĸ
    -0.29
    æĺ¯ä»ĸ
    -0.28
    çĩĶ
    -0.27
    çIJĨ
    -0.26
    aviest
    -0.26
    lius
    -0.25
    åĢŁçĶ¨
    -0.24
    his
    -0.24
     íļ
    -0.24
    POSITIVE LOGITS
     them
    0.47
     they
    0.45
    ä»ĸ们
    0.43
    ä»ĸ们éĥ½
    0.40
    她们
    0.37
    ä»ĸ们ä¼ļ
    0.36
    they
    0.35
    ä»ĸ们æĺ¯
    0.33
    ä»ĸ们çļĦ
    0.33
    them
    0.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.