© 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. 8129
    Prev
    Next
    INDEX
    Explanations

    rab

    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
    ç»Ħ
    -0.30
     switch
    -0.25
    çµĦ
    -0.25
     present
    -0.25
     dest
    -0.24
     loss
    -0.24
    讶
    -0.24
    æĥĬåı¹
    -0.24
    åģľçĶµ
    -0.24
    aysia
    -0.24
    POSITIVE LOGITS
     jewish
    0.33
    antz
    0.27
     indexer
    0.26
    âm
    0.25
    lor
    0.25
     Jewish
    0.25
    ulatory
    0.24
    ÑĨов
    0.24
    amous
    0.24
    å·¥ä½ľäººåijĺ
    0.24
    Activations Density 0.002%

    No Known Activations