© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 44238
    Prev
    Next
    INDEX
    Explanations

    extra

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
     dazu
    -0.29
    ãģªãĤĤãģ®
    -0.24
    æħ¢
    -0.24
    çªĦ
    -0.24
     up
    -0.24
    ä¸Ģæ¢Ŀ
    -0.24
     UPC
    -0.24
    offset
    -0.24
    (flags
    -0.24
    _IF
    -0.23
    POSITIVE LOGITS
    oi
    0.28
    第äºĶ
    0.28
     reinforcing
    0.28
     Patt
    0.26
    eba
    0.26
    eding
    0.26
     collaborating
    0.26
    ed
    0.25
     investing
    0.25
    oving
    0.24
    Activations Density 0.001%

    No Known Activations