© 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. 33-TRANSCODER-HP
    7. 53670
    Prev
    Next
    INDEX
    Explanations

    deep learning, images

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç®Ĺæ³ķ
    -0.55
     algorithm
    -0.53
    Algorithm
    -0.50
     Algorithm
    -0.50
     Algorithms
    -0.46
     algorithms
    -0.46
    algorithm
    -0.41
    _algorithm
    -0.40
    .algorithm
    -0.40
    algo
    -0.36
    POSITIVE LOGITS
    深度
    0.36
     deep
    0.33
     image
    0.31
     reinforcement
    0.29
    强åĮĸ
    0.28
    image
    0.26
     heels
    0.25
     Deep
    0.25
    deep
    0.24
     convolution
    0.24
    Activations Density 0.167%

    No Known Activations