© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97939
    Prev
    Next
    INDEX
    Explanations

    participants

    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
    ify
    -0.28
    zeug
    -0.26
    sut
    -0.25
     zwy
    -0.24
    punk
    -0.24
    uds
    -0.23
    fällig
    -0.23
    ardo
    -0.23
    IFY
    -0.23
    wood
    -0.23
    POSITIVE LOGITS
    nels
    0.26
    oldt
    0.26
    etro
    0.26
    /respond
    0.26
    ASTER
    0.24
    à¹Ĥ
    0.23
     multit
    0.23
    asma
    0.23
    kowski
    0.23
    ources
    0.23
    Activations Density 0.173%

    No Known Activations