© 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. 111089
    Prev
    Next
    INDEX
    Explanations

    mouths

    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
    éĺ´è°ĭ
    -0.27
    defaults
    -0.27
    ä¸įæĸŃæī©å¤§
    -0.26
     Blanch
    -0.26
     cref
    -0.26
    AndWait
    -0.26
    storybook
    -0.25
    okable
    -0.25
    :;↵
    -0.25
    maxlength
    -0.25
    POSITIVE LOGITS
    ly
    0.30
    lycer
    0.29
    dl
    0.29
    è·Į
    0.28
    oter
    0.27
    unks
    0.27
    iste
    0.27
     fen
    0.26
     regular
    0.26
     ft
    0.26
    Activations Density 0.025%

    No Known Activations