© 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. 23978
    Prev
    Next
    INDEX
    Explanations

    News events/crises

    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
    桨
    -0.26
    Ä°YE
    -0.26
    :convert
    -0.26
    ä¸įåIJĮ
    -0.25
     tie
    -0.25
    æŶéĹ´ä¸º
    -0.24
    ãģ®ãģĮ
    -0.24
     nale
    -0.24
    绳
    -0.24
    ä¸įå°½
    -0.24
    POSITIVE LOGITS
    ä½ľåĵģåĨħ容
    0.27
    umpt
    0.26
    ecc
    0.25
    maid
    0.25
    uments
    0.25
    ç©°
    0.24
     uncert
    0.24
    _aff
    0.24
     washington
    0.24
    éŃĶæľ¯
    0.24
    Activations Density 0.003%

    No Known Activations