© 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. 31-TRANSCODER-HP
    7. 19484
    Prev
    Next
    INDEX
    Explanations

    business/technical papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.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
    -0.28
    å¯Ĩ度
    -0.26
    æļĹ示
    -0.26
    ACY
    -0.25
     michael
    -0.25
    -gradient
    -0.25
    _cycle
    -0.25
    åħļçļĦé¢Ĩ导
    -0.25
    å´§
    -0.25
    oque
    -0.25
    POSITIVE LOGITS
     unp
    0.27
    讫
    0.27
     Rede
    0.27
     reb
    0.27
    lek
    0.26
    èµ
    0.26
    详
    0.25
     Produ
    0.24
    produ
    0.24
    eries
    0.24
    Activations Density 21.377%

    No Known Activations