© 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. 30-TRANSCODER-HP
    7. 96948
    Prev
    Next
    INDEX
    Explanations

    We

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åħ·æľīèī¯å¥½
    -0.29
    件äºĭ
    -0.26
    çļĦäºĭ
    -0.26
    åķĦ
    -0.25
    èĮ¹
    -0.25
    å¤ķ
    -0.25
    åľ°çIJĥä¸Ĭ
    -0.25
    Must
    -0.24
    ä»Ģä¹ĪåİŁåĽł
    -0.23
    ACHE
    -0.23
    POSITIVE LOGITS
     hadn
    0.32
     recognized
    0.29
    çľĭå¾ħ
    0.28
     noticed
    0.27
    erview
    0.27
    å·¥ä½ľæĬ¥åijĬ
    0.27
    recognized
    0.26
    ä¸ĢæĿ¡é¾Ļ
    0.26
     simply
    0.25
    avorite
    0.25
    Activations Density 0.903%

    No Known Activations