© 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. 23-TRANSCODER-HP
    7. 23379
    Prev
    Next
    INDEX
    Explanations

    mis-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    voir
    -0.27
    official
    -0.27
    仪å¼ı
    -0.26
    ARA
    -0.25
    odo
    -0.25
    ãģ¹ãģį
    -0.25
    éĥ¨åī¯éĥ¨éķ¿
    -0.24
    .Root
    -0.24
    è§Ī
    -0.24
    ç¿ĺ
    -0.24
    POSITIVE LOGITS
     mutual
    0.29
     fatal
    0.26
    y
    0.26
    ror
    0.26
     inse
    0.25
    äºĨæĪijçļĦ
    0.25
    uhan
    0.24
    anium
    0.24
    å¯Ĩ
    0.24
    rij
    0.24
    Activations Density 0.027%

    No Known Activations