© 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. 40829
    Prev
    Next
    INDEX
    Explanations

    departments

    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
     ad
    -0.27
    ken
    -0.26
    bic
    -0.26
    amer
    -0.25
    å¹²
    -0.25
    ads
    -0.25
     america
    -0.24
    ç¾İæ´²
    -0.24
     adaptive
    -0.24
    ç©¿éĢı
    -0.24
    POSITIVE LOGITS
    éĥ¨éŨ
    0.43
     department
    0.40
     Department
    0.38
     departments
    0.36
    Department
    0.34
     Departments
    0.34
    éĥ¨éĸĢ
    0.33
    éĥ¨
    0.33
    åIJĦéĥ¨éŨ
    0.33
     Depart
    0.32
    Activations Density 0.001%

    No Known Activations