© 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. 27-TRANSCODER-HP
    7. 58042
    Prev
    Next
    INDEX
    Explanations

    parallel computing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     royalties
    -0.27
    ensed
    -0.26
     Bookmark
    -0.26
    ucid
    -0.26
    adium
    -0.25
    ä¸ĭ车
    -0.25
    ldb
    -0.25
     Numer
    -0.25
    -db
    -0.24
     Bureau
    -0.24
    POSITIVE LOGITS
     parallel
    0.54
    å¹³è¡Į
    0.46
     Parallel
    0.45
    GPU
    0.44
    parallel
    0.41
    gpu
    0.41
     paralle
    0.41
    cpu
    0.41
    Parallel
    0.40
    cuda
    0.40
    Activations Density 0.008%

    No Known Activations