© 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. 97236
    Prev
    Next
    INDEX
    Explanations

    is, was

    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
    丰å¯Įå¤ļ彩
    -0.26
    åħļåĴĮåĽ½å®¶
    -0.26
    rax
    -0.25
    .Fl
    -0.24
    åĩºæīĭ
    -0.24
    dance
    -0.24
    å¥ij约
    -0.24
    rch
    -0.24
    -ren
    -0.23
    äºĮ线
    -0.23
    POSITIVE LOGITS
    ç«Ļ
    0.35
    eness
    0.31
    .LogInformation
    0.27
    满
    0.27
    adel
    0.27
    åħ¨
    0.27
    aka
    0.26
    ä¸įåİ»
    0.26
    :auto
    0.25
    /auto
    0.25
    Activations Density 0.007%

    No Known Activations