© 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. 22-TRANSCODER-HP
    7. 129163
    Prev
    Next
    INDEX
    Explanations

    People in narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Covered
    -0.28
    è¿Ļæł·æīįèĥ½
    -0.28
    ä»ĬæĻļ
    -0.25
    (Context
    -0.25
    earer
    -0.25
    è´´
    -0.25
    gram
    -0.24
    ersh
    -0.24
    vi
    -0.24
    åİŁçIJĨ
    -0.24
    POSITIVE LOGITS
     Keto
    0.26
    ä¸Ģè§Ĵ
    0.25
     frei
    0.25
    ä¸Ģç»ı
    0.25
    apult
    0.25
    å¼Ĥåľ°
    0.24
    å¾Ĺ太
    0.24
    SSIP
    0.24
    emade
    0.24
    osite
    0.23
    Activations Density 0.002%

    No Known Activations