© 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. 23-TRANSCODER-HP
    7. 25437
    Prev
    Next
    INDEX
    Explanations

    software code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -before
    -0.48
     before
    -0.45
     Before
    -0.41
    before
    -0.41
    Before
    -0.40
     BEFORE
    -0.39
    	before
    -0.39
    æħİéĩį
    -0.37
    è°¨æħİ
    -0.36
    åľ¨æѤä¹ĭåīį
    -0.36
    POSITIVE LOGITS
    ubar
    0.28
    meye
    0.28
     Hill
    0.26
    ä¸įåıĬ
    0.26
     Nope
    0.26
    继ç»Ń
    0.25
    赶快
    0.25
    iversary
    0.24
    iou
    0.24
    .ErrorCode
    0.23
    Activations Density 0.005%

    No Known Activations