© 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. 32-TRANSCODER-HP
    7. 41354
    Prev
    Next
    INDEX
    Explanations

    Arbitrary text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vit
    -0.39
     h
    -0.36
    æŀľ
    -0.34
     fruit
    -0.33
    设æĸ½
    -0.32
    åĩ¿
    -0.31
     rose
    -0.30
    èĭ¹æŀľ
    -0.28
     Fruit
    -0.28
    èıľ
    -0.27
    POSITIVE LOGITS
    çĶ°
    0.54
     fields
    0.49
     farm
    0.49
     farms
    0.46
     crop
    0.43
     farming
    0.42
     farmers
    0.42
     Fields
    0.41
     crops
    0.41
    åĨľçĶ°
    0.40
    Activations Density 0.001%

    No Known Activations