© 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. 43397
    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
     вал
    -0.27
    ca
    -0.26
     unity
    -0.26
    山谷
    -0.25
    ooled
    -0.25
    astically
    -0.24
    ida
    -0.24
    åģľè½¦ä½į
    -0.24
    .getAddress
    -0.24
     scratches
    -0.24
    POSITIVE LOGITS
    estone
    0.28
    æªIJ
    0.25
     tslib
    0.25
    èŃ
    0.25
     decorators
    0.25
    éħŀ
    0.24
    cip
    0.24
    endo
    0.24
    abar
    0.24
    å°¤åħ¶æĺ¯åľ¨
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.