© 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. 12-TRANSCODER-HP
    7. 23606
    Prev
    Next
    INDEX
    Explanations

    Articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agnost
    -0.26
    沤
    -0.26
    equality
    -0.26
    autop
    -0.25
     gyr
    -0.24
    icing
    -0.24
     autop
    -0.24
     Associ
    -0.24
    ä¼Ļ
    -0.24
    portun
    -0.23
    POSITIVE LOGITS
    :index
    0.25
    åĬŀ
    0.24
    æĺ´
    0.24
    shake
    0.24
    裳
    0.24
    ç´¢
    0.24
     Won
    0.23
    è¿ĺæĺ¯ä¼ļ
    0.23
    æľªçŁ¥
    0.23
    è¯Ĭæ²»
    0.23
    Activations Density 0.001%

    No Known Activations