© 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. 23466
    Prev
    Next
    INDEX
    Explanations

    Web suffixes

    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
    åĪ«
    -0.28
    å±Ģ
    -0.27
    ä»Ģä¹Īåij¢
    -0.27
    ás
    -0.27
    ç±
    -0.26
    á»ĭa
    -0.25
    à¹Īà¸Ńย
    -0.25
    üh
    -0.25
    ừng
    -0.25
    èĩ´
    -0.25
    POSITIVE LOGITS
     schl
    0.27
     milano
    0.25
    recipes
    0.25
    HasBeenSet
    0.25
     Happ
    0.25
    ope
    0.24
     convo
    0.23
     Goodman
    0.23
     combos
    0.23
    clipse
    0.23
    Activations Density 0.003%

    No Known Activations