© 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. 88967
    Prev
    Next
    INDEX
    Explanations

    File beginnings/endings

    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
    å¾ĢåIJİ
    -0.25
    ethical
    -0.24
    fetchAll
    -0.23
    åıijçĶŁäºĨ
    -0.23
    IBUT
    -0.23
     smack
    -0.23
     bombed
    -0.23
    /******/
    -0.23
     ::↵
    -0.23
    TERS
    -0.23
    POSITIVE LOGITS
    -E
    0.52
    -G
    0.50
    -B
    0.49
    -H
    0.48
    -S
    0.48
    -M
    0.48
    -F
    0.48
    -K
    0.48
    -D
    0.47
    -J
    0.46
    Activations Density 0.149%

    No Known Activations