© 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. 87120
    Prev
    Next
    INDEX
    Explanations

    Advocate and champion

    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
    Outside
    -0.30
     Outside
    -0.29
    .si
    -0.28
    contract
    -0.27
    contracts
    -0.25
    æ·Į
    -0.25
    outside
    -0.25
    isateur
    -0.23
    container
    -0.23
    vens
    -0.23
    POSITIVE LOGITS
    ULO
    0.26
     pairing
    0.25
    acular
    0.25
     trade
    0.25
    -for
    0.24
    ÙĤر
    0.24
    èĢħçļĦ
    0.23
    ulos
    0.23
     natural
    0.23
    ×ĺר×Ķ
    0.22
    Activations Density 0.045%

    No Known Activations