© 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. 21929
    Prev
    Next
    INDEX
    Explanations

    1

    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
     scrapped
    -0.26
     vending
    -0.26
    ality
    -0.25
    âte
    -0.25
    latable
    -0.24
    åı¤ä»Ĭ
    -0.24
    ughter
    -0.23
     departing
    -0.23
     replaced
    -0.23
    è¨ĢãģĪãģ°
    -0.23
    POSITIVE LOGITS
     rog
    0.27
    èĮĥæĸĩ
    0.27
    åįķ身
    0.26
    orent
    0.26
     Rog
    0.25
    ilename
    0.25
    ç²¾
    0.24
     complete
    0.24
    ':{'
    0.24
    ])-
    0.24
    Activations Density 0.001%

    No Known Activations