© 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. 33-TRANSCODER-HP
    7. 52753
    Prev
    Next
    INDEX
    Explanations

    Gene/code sequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ro
    -0.29
    KER
    -0.28
     ib
    -0.26
    Ļ¶
    -0.25
    ocr
    -0.25
    åĬ¨æľº
    -0.24
    lide
    -0.24
    hee
    -0.24
    į°ìĿ´
    -0.24
     unb
    -0.24
    POSITIVE LOGITS
    ACT
    0.58
    TT
    0.56
    CAA
    0.56
    CCA
    0.56
    TC
    0.56
    CT
    0.55
    act
    0.54
    atat
    0.54
    ct
    0.53
    GG
    0.53
    Activations Density 0.015%

    No Known Activations