© 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. 27-TRANSCODER-HP
    7. 7901
    Prev
    Next
    INDEX
    Explanations

    Proper nouns or titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ères
    -0.29
    ä¸į对
    -0.29
     flap
    -0.28
    ulação
    -0.26
    ectl
    -0.26
     grip
    -0.26
    解åĨ³
    -0.24
    ULATOR
    -0.24
    .getActivity
    -0.23
     conf
    -0.23
    POSITIVE LOGITS
    éĹ®
    0.29
     Haz
    0.29
     haz
    0.28
    Haz
    0.27
    éĢļçĶ¨
    0.27
    Still
    0.26
    éĹ®çŃĶ
    0.26
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.26
     CSA
    0.26
     promot
    0.26
    Activations Density 0.000%

    No Known Activations