© 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. 20-TRANSCODER-HP
    7. 63786
    Prev
    Next
    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    令
    -0.27
     behave
    -0.26
    anga
    -0.25
    æ®Ĩ
    -0.25
    çİ·
    -0.25
    ido
    -0.24
     behaving
    -0.24
     PCs
    -0.24
     gridSize
    -0.24
    nero
    -0.24
    POSITIVE LOGITS
    opsis
    0.26
    åµĮ
    0.26
    Tbl
    0.26
    è±ģ
    0.25
    çĸı
    0.25
     '`
    0.25
    两ä¼ļ
    0.25
    .om
    0.24
     Pais
    0.24
    媳
    0.24
    Activations Density 7.335%

    No Known Activations