© 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. 113013
    Prev
    Next
    INDEX
    Explanations

    Code and programming 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
    mis
    -0.31
    BOOST
    -0.26
    åĩŃ
    -0.26
    çݯ
    -0.26
    群
    -0.25
    MISS
    -0.25
    miss
    -0.25
     boosting
    -0.24
    jav
    -0.24
    etrics
    -0.24
    POSITIVE LOGITS
     identical
    0.41
    缸åIJĮ
    0.41
     differing
    0.40
    缸åIJĮçļĦ
    0.39
    åIJĮçŃī
    0.39
    æľīæīĢä¸įåIJĮ
    0.38
    vens
    0.35
     comparable
    0.35
     different
    0.34
     unterschied
    0.33
    Activations Density 0.011%

    No Known Activations