© 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. 24163
    Prev
    Next
    INDEX
    Explanations

    ench

    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
    odiac
    -0.31
     Bene
    -0.27
    rand
    -0.26
    IENTATION
    -0.26
     Äijẳng
    -0.25
    rese
    -0.25
    ucker
    -0.25
    å¢ĥ
    -0.24
    letal
    -0.24
     getHeight
    -0.24
    POSITIVE LOGITS
    hya
    0.30
    åıįé¦Ī
    0.29
    åı¯è§Ĩ
    0.25
     feedback
    0.24
    头æĿ¡
    0.24
     weblog
    0.24
    smith
    0.23
    æµij身
    0.23
     confer
    0.23
    Trip
    0.23
    Activations Density 0.001%

    No Known Activations