© 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. 20-TRANSCODER-HP
    7. 130103
    Prev
    Next
    INDEX
    Explanations

    Processes or stages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ĺæľª
    -0.32
    å°ļæľª
    -0.32
    /packages
    -0.26
    uja
    -0.26
    å½±åĵįåĬĽçļĦ
    -0.24
    å½Ĵ
    -0.24
    orning
    -0.24
     READY
    -0.24
    uco
    -0.24
    issan
    -0.24
    POSITIVE LOGITS
    och
    0.27
    ause
    0.26
    人æ°ijæľįåĬ¡
    0.24
    åºĹéĿ¢
    0.24
    osc
    0.24
    oise
    0.24
    ãĤĤãģĹ
    0.23
    mus
    0.23
    ä¹°åįķ
    0.23
    ä¸įèĥ½ä¸ºç©º
    0.23
    Activations Density 9.075%

    No Known Activations