© 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. 86836
    Prev
    Next
    INDEX
    Explanations

    review

    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
    cot
    -0.30
     дÑĥÑħ
    -0.28
    åħ·
    -0.27
     cot
    -0.27
    æŀļ
    -0.24
    ìºĶ
    -0.24
    çłĶ究表æĺİ
    -0.24
    Generation
    -0.23
    æľºæ¢°è®¾å¤ĩ
    -0.23
     presence
    -0.23
    POSITIVE LOGITS
    final
    0.26
    rias
    0.25
    esa
    0.25
    éķ¿å¤§äºĨ
    0.24
     GUID
    0.24
    imus
    0.24
    esen
    0.24
    UMB
    0.24
    ardy
    0.24
    }}],↵
    0.24
    Activations Density 0.069%

    No Known Activations