© 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. 32-TRANSCODER-HP
    7. 40893
    Prev
    Next
    INDEX
    Explanations

    Code or foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     select
    -0.28
     directions
    -0.27
     common
    -0.27
    è¾¹
    -0.27
    xes
    -0.27
    ilos
    -0.27
     Select
    -0.26
     done
    -0.26
    ippo
    -0.26
     dynamic
    -0.25
    POSITIVE LOGITS
    éĽĩ主
    0.26
    hea
    0.24
    quire
    0.24
    对åŃ©åŃIJ
    0.24
    åĪ°æĿ¥
    0.24
    gne
    0.24
    好äºĨ
    0.23
     Li
    0.23
    æŁ³
    0.23
    HX
    0.23
    Activations Density 0.001%

    No Known Activations