© 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. 32-TRANSCODER-HP
    7. 41876
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĽ·è¾¾
    -0.27
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    -0.25
     Rue
    -0.25
    å±
    -0.24
    &W
    -0.24
    幡
    -0.24
    è«ĩ
    -0.23
     gear
    -0.23
    .FILES
    -0.23
    etri
    -0.23
    POSITIVE LOGITS
    äºĶåĽĽ
    0.28
    aira
    0.27
    ately
    0.27
    >\<
    0.27
    airo
    0.26
    æĹłåĬ©
    0.26
    оÑģÑĤи
    0.26
    itto
    0.25
     Anat
    0.25
    æł¡
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.