© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129872
    Prev
    Next
    INDEX
    Explanations

    code/programming related text

    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
    widgets
    -0.26
    èµģ
    -0.24
     launder
    -0.23
    æĮģæľīçļĦ
    -0.23
     babes
    -0.23
    åĿIJçĿĢ
    -0.22
    æİ·
    -0.22
    Gain
    -0.22
    ylabel
    -0.22
    诸
    -0.22
    POSITIVE LOGITS
    ãĤ½ãĥ¼
    0.27
    worthy
    0.26
    -related
    0.25
    zew
    0.25
     inter
    0.24
    å¥Ń
    0.24
     larger
    0.24
    æ½į
    0.24
     often
    0.23
    cao
    0.23
    Activations Density 0.001%

    No Known Activations