© 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. 110917
    Prev
    Next
    INDEX
    Explanations

    legal documents, names

    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
     downright
    -0.27
    å½ĵä¸Ń
    -0.26
    dead
    -0.26
     Blow
    -0.26
    tures
    -0.25
    交éĶĻ
    -0.25
    wart
    -0.25
     meetup
    -0.25
    便ä¼ļ
    -0.25
     supposedly
    -0.24
    POSITIVE LOGITS
    iene
    0.28
    aclass
    0.26
    çīĮ
    0.25
    arra
    0.25
    aru
    0.25
    opia
    0.24
     æ
    0.24
    å¼Ĥ
    0.24
    ika
    0.24
    PIX
    0.23
    Activations Density 0.084%

    No Known Activations