© 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. 97538
    Prev
    Next
    INDEX
    Explanations

    Computing/Technology

    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
     Dank
    -0.27
    astro
    -0.27
     built
    -0.26
    ĺ认
    -0.26
    umont
    -0.26
     Built
    -0.25
     bindings
    -0.25
     round
    -0.24
     decorated
    -0.24
    >>::
    -0.24
    POSITIVE LOGITS
    éģŃéģĩ
    0.36
    åģľçĶµ
    0.35
    éģŃåıĹ
    0.35
    æĦıå¤ĸ
    0.34
    丢失
    0.31
    lost
    0.30
    ä¸įæħİ
    0.29
    失èIJ½
    0.29
    失误
    0.28
    æĴŀåĩ»
    0.28
    Activations Density 0.005%

    No Known Activations