© 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. 87046
    Prev
    Next
    INDEX
    Explanations

    Code/Documentation Snippets

    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
     Britann
    -0.27
    errer
    -0.27
    翦
    -0.25
    åīª
    -0.24
    åIJŁ
    -0.24
     Flash
    -0.24
    iones
    -0.24
     Lama
    -0.24
     Nim
    -0.23
    èĥĮ
    -0.23
    POSITIVE LOGITS
    è¾Ł
    0.29
    缴åįĩ
    0.25
     removeFrom
    0.25
    AIL
    0.25
    áln
    0.25
    ifier
    0.24
    -suite
    0.24
    òng
    0.24
    äre
    0.23
     Beet
    0.23
    Activations Density 0.000%

    No Known Activations