© 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. 12-TRANSCODER-HP
    7. 24058
    Prev
    Next
    INDEX
    Explanations

    Systems management/monitoring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Lean
    -0.27
     ref
    -0.27
     ret
    -0.27
     occupies
    -0.26
    bine
    -0.26
    æŀģ大
    -0.26
     Insert
    -0.26
    à¹Ĥà¸Ľà¸£à¸Ķ
    -0.26
    ven
    -0.26
    acd
    -0.26
    POSITIVE LOGITS
    ä¼ļéĢīæĭ©
    0.26
    inally
    0.25
    hips
    0.25
    amenti
    0.25
    ä¼ļéķ¿
    0.25
    SIM
    0.24
    ä¸įçĦ¶
    0.24
    Directories
    0.24
    ¥
    0.24
    ä¸įæŃ»
    0.24
    Activations Density 0.001%

    No Known Activations