© 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. 129903
    Prev
    Next
    INDEX
    Explanations

    News articles/Press releases

    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
     branch
    -0.27
    åīµæ¥Ń
    -0.26
     constructive
    -0.25
    weather
    -0.25
    æĹħéģĬ
    -0.24
     ther
    -0.24
    edis
    -0.23
    èݼ
    -0.23
    ì¡°
    -0.23
     weather
    -0.23
    POSITIVE LOGITS
     inversion
    0.27
    ä¸Ģçľĭ
    0.26
     Kash
    0.26
    çļĦæĥħ
    0.26
    å´½
    0.25
     Meyer
    0.24
    itud
    0.24
    æĦıæĦ¿
    0.24
    åIJįä¹ī
    0.24
     Ire
    0.24
    Activations Density 0.030%

    No Known Activations