© 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. 107509
    Prev
    Next
    INDEX
    Explanations

    negative statements or problems

    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
    èĢģå©Ĩ
    -0.27
    ç«¿
    -0.26
    帮å¿Ļ
    -0.26
     stagger
    -0.26
     Wife
    -0.25
     scrut
    -0.25
    ë§ī
    -0.25
    夸大
    -0.24
    лав
    -0.24
    妻
    -0.24
    POSITIVE LOGITS
    第äºĮ次
    0.40
    第ä¸ī次
    0.30
    ationship
    0.30
    两次
    0.28
     twice
    0.28
    äºĮ次
    0.26
    yle
    0.26
    ä¸įåĸľæ¬¢
    0.26
    -Ray
    0.25
    åľ¨åIJĮä¸Ģ
    0.25
    Activations Density 27.860%

    No Known Activations