© 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. 12-TRANSCODER-HP
    7. 24253
    Prev
    Next
    INDEX
    Explanations

    week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     vacations
    -0.27
    éĻ¢
    -0.24
    ÑģÑĤолÑĮ
    -0.24
    imators
    -0.24
     plein
    -0.24
    åij¨æľ«
    -0.24
    æĹ©é¤IJ
    -0.23
    nants
    -0.23
    ä¹ĭç±»çļĦ
    -0.23
    ël
    -0.23
    POSITIVE LOGITS
    wij
    0.29
    lias
    0.28
    åĽºå®ļçļĦ
    0.28
    Sid
    0.27
    wis
    0.26
    çªģ
    0.26
     union
    0.25
    wc
    0.25
     Cub
    0.25
    li
    0.25
    Activations Density 0.006%

    No Known Activations