© 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. 88994
    Prev
    Next
    INDEX
    Explanations

    Asking questions

    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
    ething
    -0.30
    izando
    -0.27
    lsx
    -0.25
    пÑĥÑĤ
    -0.25
    ùng
    -0.24
     IDF
    -0.24
    '+↵
    -0.24
     ...)↵
    -0.24
    }*/↵↵
    -0.23
     MST
    -0.23
    POSITIVE LOGITS
    /articles
    0.25
     boss
    0.25
    å¾Ĺä½ı
    0.24
     begins
    0.24
     venez
    0.24
    @show
    0.24
    åĢ¼å¾Ĺä¸Ģ
    0.24
    sounds
    0.24
    ãģªãĤĭ
    0.23
    åĵĢ
    0.23
    Activations Density 0.028%

    No Known Activations