© 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. 88937
    Prev
    Next
    INDEX
    Explanations

    rights

    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
    æľīæŶ
    -0.32
     sometimes
    -0.28
    æľīæŶåĢĻ
    -0.27
    å¾Īå¤ļæŶåĢĻ
    -0.27
    degrees
    -0.26
    交æİ¥
    -0.26
    åij½
    -0.26
     Lew
    -0.25
     quir
    -0.25
    å¥Ĺ
    -0.25
    POSITIVE LOGITS
    yth
    0.28
    yre
    0.26
     disturbed
    0.26
    irez
    0.25
    ikk
    0.25
    æļĤåģľ
    0.24
    ieber
    0.24
    ä¹ĥ
    0.23
     resumes
    0.23
    .Screen
    0.23
    Activations Density 0.021%

    No Known Activations