© 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. 130517
    Prev
    Next
    INDEX
    Explanations

    various fields

    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
    åºĬä¸Ĭ
    -0.28
    èĻ¹
    -0.26
     Kr
    -0.24
    åºŀ
    -0.23
    lices
    -0.23
    èĭ´
    -0.23
    åĺĽ
    -0.23
     pleasure
    -0.23
     Pole
    -0.23
     through
    -0.23
    POSITIVE LOGITS
    ugin
    0.28
     déc
    0.26
    æĬĸ
    0.25
    _/
    0.25
    \Blueprint
    0.24
    æĬĬè¿ĻäºĽ
    0.24
    ategories
    0.23
    ä¹Łéĥ½
    0.23
    é¢ľèī²
    0.23
    æĤłæĤł
    0.23
    Activations Density 0.006%

    No Known Activations