© 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. 40823
    Prev
    Next
    INDEX
    Explanations

    Mer

    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
    mono
    -0.28
    éĥ¨éĥ¨éķ¿
    -0.28
    äºļåĨĽ
    -0.27
     Central
    -0.26
     replica
    -0.24
     monot
    -0.24
    artment
    -0.24
    ora
    -0.23
    å¤ı
    -0.23
    åī¯æĢ»è£ģ
    -0.23
    POSITIVE LOGITS
    å®ģ
    0.26
     meth
    0.25
    jsc
    0.25
    çe
    0.25
    èĭŁ
    0.25
    maids
    0.25
    æ¦Ĩ
    0.25
    leg
    0.25
     Meth
    0.24
    gba
    0.24
    Activations Density 0.003%

    No Known Activations