© 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. 63921
    Prev
    Next
    INDEX
    Explanations

    Stopwords in complex sentences

    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
    -spin
    -0.28
    èºį
    -0.28
    ä¼łæĿ¥
    -0.28
    ãģª
    -0.27
    ication
    -0.25
    avit
    -0.24
    .Inter
    -0.24
    “I
    -0.24
    atan
    -0.23
    æ¯ıåij¨
    -0.23
    POSITIVE LOGITS
    comb
    0.28
    å®ŀè´¨
    0.26
     comb
    0.26
    æѦè£ħ
    0.26
     offence
    0.26
    è¿Ŀç«ł
    0.26
    è¿ĩçļĦ
    0.25
    èݺ
    0.25
     offense
    0.25
    èļķ
    0.25
    Activations Density 12.282%

    No Known Activations