© 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. 24-TRANSCODER-HP
    7. 151223
    Prev
    Next
    INDEX
    Explanations

    time passing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    sharing
    -0.30
    åħ¼
    -0.29
    =length
    -0.28
    packing
    -0.26
    æīĢå¾Ĺ
    -0.26
    hyp
    -0.26
    incr
    -0.25
    æľīå¤ļ大
    -0.25
     sharing
    -0.25
     crumbs
    -0.25
    POSITIVE LOGITS
     late
    0.26
    礼
    0.26
    Adj
    0.26
     March
    0.26
     recon
    0.25
     loose
    0.25
     adj
    0.25
    禮
    0.25
     after
    0.24
    人家
    0.24
    Activations Density 0.173%

    No Known Activations