© 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. 87838
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    è¿Ľ
    -0.27
    agement
    -0.27
    eme
    -0.26
    MER
    -0.26
    inem
    -0.25
    mai
    -0.24
    azole
    -0.24
    产åIJİ
    -0.24
     herself
    -0.24
    æĦıæĢĿ
    -0.23
    POSITIVE LOGITS
    ä¸Ģéĥ¨
    0.26
    æĹ¥åŃIJ
    0.26
    å®ĥåı¯ä»¥
    0.25
    DDS
    0.24
    iling
    0.24
    issent
    0.24
    ampp
    0.24
     uncomp
    0.24
    è¿ĻäºĽéĹ®é¢ĺ
    0.24
    eties
    0.24
    Activations Density 0.005%

    No Known Activations