© 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. 22-TRANSCODER-HP
    7. 129055
    Prev
    Next
    INDEX
    Explanations

    Levels of severity or size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Ptr
    -0.27
     converge
    -0.27
    åĴĮå®ĮåĸĦ
    -0.27
    æĶ¶æķĽ
    -0.27
    ocoa
    -0.27
    Appro
    -0.26
    è¿ĩé«ĺ
    -0.26
     converged
    -0.26
    ä»ħä¾ĽåıĤèĢĥ
    -0.25
    çķ¥æľī
    -0.25
    POSITIVE LOGITS
     quantity
    0.26
    ango
    0.24
    PropertyChanged
    0.24
    typ
    0.24
    QP
    0.24
    :request
    0.23
    '</
    0.23
     support
    0.23
    åĬ¨çĶŁæĪIJ
    0.23
     deb
    0.23
    Activations Density 0.006%

    No Known Activations