© 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. 24-TRANSCODER-HP
    7. 150746
    Prev
    Next
    INDEX
    Explanations

    computer software/hardware

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    称ä¹ĭ
    -0.30
     Assertion
    -0.29
    ogonal
    -0.28
     unzip
    -0.26
    SELL
    -0.26
     zipper
    -0.25
    à¹Ĥà¸Ħร
    -0.25
    å¼ĢåºĹ
    -0.25
    embed
    -0.25
     outer
    -0.25
    POSITIVE LOGITS
    çIJ¼
    0.29
    éĢīæĭĶ
    0.26
    ä¼°ç®Ĺ
    0.26
    åĩŃ
    0.25
    .ev
    0.25
    лÑıем
    0.24
    urch
    0.24
     lowering
    0.24
     enduring
    0.24
    è¿Ļ次
    0.23
    Activations Density 0.130%

    No Known Activations