© 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. 129583
    Prev
    Next
    INDEX
    Explanations

    enormous

    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
    tle
    -0.27
    缸åħ³æĸ°éĹ»
    -0.25
    perature
    -0.24
    rou
    -0.24
    çĪ·
    -0.24
    EOS
    -0.23
     Nähe
    -0.23
    Rec
    -0.23
    ä¹Ļ
    -0.23
     whistle
    -0.22
    POSITIVE LOGITS
    pike
    0.30
    sworth
    0.26
    ityEngine
    0.25
    ness
    0.24
    sı
    0.24
    -lasting
    0.23
    foy
    0.23
    ates
    0.23
    åįļè§Īä¼ļ
    0.23
    ancell
    0.23
    Activations Density 0.258%

    No Known Activations