© 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. 25359
    Prev
    Next
    INDEX
    Explanations

    phone numbers, patents

    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
     gast
    -0.27
     mathematic
    -0.26
    æĤ¨å¥½
    -0.26
     heading
    -0.25
    Ľ
    -0.25
    人大代表
    -0.25
    apos
    -0.25
    icks
    -0.25
    uced
    -0.24
    arters
    -0.24
    POSITIVE LOGITS
    éªij
    0.29
    anship
    0.26
    afil
    0.26
    arov
    0.25
    ching
    0.25
     Connie
    0.25
    ENCE
    0.24
    è¯ŀçĶŁ
    0.24
    ean
    0.24
    omination
    0.24
    Activations Density 0.061%

    No Known Activations