© 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. 88778
    Prev
    Next
    INDEX
    Explanations

    Mixed text snippets

    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
     similar
    -0.40
    similar
    -0.36
     Similar
    -0.35
    Similar
    -0.33
     simil
    -0.31
    çĽ¸ä¼¼
    -0.31
     similarly
    -0.29
    类似
    -0.28
    ose
    -0.28
    类似çļĦ
    -0.27
    POSITIVE LOGITS
    STYPE
    0.25
    asje
    0.25
    itzer
    0.24
     seja
    0.24
    ä¸ĢåĪĨ
    0.24
    tures
    0.23
    è¿Ļå°±æĺ¯
    0.23
    è´¶
    0.23
     DISPLAY
    0.23
    ivement
    0.23
    Activations Density 0.003%

    No Known Activations