© 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. 22121
    Prev
    Next
    INDEX
    Explanations

    alongside

    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
    rones
    -0.27
    itated
    -0.27
    ience
    -0.27
    æĸ°åŀĭ
    -0.27
    rench
    -0.27
    .dr
    -0.26
    æ³¥åľŁ
    -0.26
    æĽ´æľī
    -0.26
    ä¸ĢåIJį
    -0.25
     roman
    -0.25
    POSITIVE LOGITS
     ministries
    0.26
    кÑĥп
    0.26
    afc
    0.25
    å°ı游æĪı
    0.25
    postData
    0.25
    VG
    0.24
    flashdata
    0.24
    çĶ¨å¾®ä¿¡
    0.24
    datap
    0.23
    ä¸ĭåıij
    0.23
    Activations Density 0.799%

    No Known Activations