© 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. 25373
    Prev
    Next
    INDEX
    Explanations

    Verbs of saying

    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
    ียà¸Ļ
    -0.28
    ä½Ĩçİ°åľ¨
    -0.27
    æĨĭ
    -0.26
    ace
    -0.25
    ze
    -0.24
     dan
    -0.24
    ecc
    -0.24
    å¾ģéĽĨ
    -0.24
     uncert
    -0.23
    çĸ²
    -0.23
    POSITIVE LOGITS
     showing
    0.29
     noting
    0.27
     correl
    0.26
    “A
    0.26
    Showing
    0.26
    Documents
    0.26
    认为
    0.25
    å®ĥ
    0.25
     Nó
    0.25
     adding
    0.25
    Activations Density 0.009%

    No Known Activations