© 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. 112909
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
     wig
    -0.29
    äºĶå®ĺ
    -0.27
    wig
    -0.25
     flagged
    -0.25
     lehet
    -0.25
    inear
    -0.24
    boarding
    -0.24
     illegally
    -0.23
     nowhere
    -0.23
     LEG
    -0.23
    POSITIVE LOGITS
    imulator
    0.28
     organisers
    0.27
    çĮĽ
    0.25
    rá
    0.25
    fa
    0.25
    å£ķ
    0.25
     Observer
    0.24
    ä½ľèĢħ
    0.24
    çIJĨ念
    0.24
    chalk
    0.24
    Activations Density 0.034%

    No Known Activations