© 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. 24025
    Prev
    Next
    INDEX
    Explanations

    Computer code and technical documentation

    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
    主æŨ
    -0.28
    å±ŀæĢ§
    -0.26
     kos
    -0.26
    足足
    -0.26
    iard
    -0.26
     addict
    -0.25
     inventor
    -0.25
    :].
    -0.24
    æľīåĬ©
    -0.24
    对ä»ĸ们
    -0.24
    POSITIVE LOGITS
     ench
    0.28
    Ñıем
    0.26
    EIF
    0.26
    ä»ħä¾Ľ
    0.25
    ý
    0.25
     Lage
    0.25
    (DIR
    0.25
     nghiá»ĩm
    0.24
    etti
    0.24
    alendar
    0.23
    Activations Density 0.001%

    No Known Activations