© 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. 18-TRANSCODER-HP
    7. 88329
    Prev
    Next
    INDEX
    Explanations

    mixed text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸ĸçķĮä¸ĬæľĢ
    -0.27
    ohn
    -0.27
     intr
    -0.26
     stress
    -0.25
    clearfix
    -0.25
    ä¼Łå¤§çļĦ
    -0.25
    ä¸įä¸Ģæł·çļĦ
    -0.25
    亲çĪ±çļĦ
    -0.25
    èľ
    -0.25
    zá
    -0.25
    POSITIVE LOGITS
     jon
    0.27
     Zuk
    0.26
     outf
    0.25
     prow
    0.25
     Grad
    0.25
    æķ¢
    0.24
     lookahead
    0.24
    ç®Ń
    0.24
    @qq
    0.23
     cine
    0.23
    Activations Density 1.862%

    No Known Activations