© 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. 27-TRANSCODER-HP
    7. 9686
    Prev
    Next
    INDEX
    Explanations

    Vet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åħĢ
    -0.30
    pei
    -0.28
    åѤåįķ
    -0.26
     protector
    -0.25
    æħ¢æħ¢çļĦ
    -0.25
     unp
    -0.24
    atism
    -0.24
    redi
    -0.23
     pies
    -0.23
    blo
    -0.23
    POSITIVE LOGITS
    Human
    0.28
    è¿Ļæł·çļĦ
    0.27
    expiration
    0.27
     Human
    0.26
     Spacer
    0.26
    cion
    0.26
    æİ¥åĪ°
    0.26
    ãĤ¤ãĥ«
    0.25
    (gen
    0.25
    åĪ·
    0.25
    Activations Density 1.067%

    No Known Activations