© 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. 129264
    Prev
    Next
    INDEX
    Explanations

    patient

    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
    Not in Any Lists

    No Comments

    Negative Logits
     D
    -0.30
    ä½ı
    -0.28
    æĩĤå¾Ĺ
    -0.28
    ä½ıåľ¨
    -0.26
     Gr
    -0.26
     ka
    -0.25
    ATER
    -0.25
    ater
    -0.25
    .Gr
    -0.25
     inst
    -0.25
    POSITIVE LOGITS
     TSRMLS
    0.29
     Hwy
    0.26
    缸åħ³æĸ°éĹ»
    0.26
    éĽ¢ãĤĮ
    0.26
    .esp
    0.26
    ôme
    0.26
    ustralian
    0.25
    аÑģÑģив
    0.25
    orning
    0.25
    åĪĸ
    0.25
    Activations Density 0.299%

    No Known Activations