© 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. 108082
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    popular
    -0.27
    æ±¾
    -0.26
    ç§ĭåŃ£
    -0.26
    éļ°
    -0.25
     SE
    -0.24
     popular
    -0.24
    istik
    -0.24
    uously
    -0.24
     Isis
    -0.24
    FileVersion
    -0.24
    POSITIVE LOGITS
     linspace
    0.27
    éŀł
    0.27
    å¸ĺ
    0.26
    ä»»ä½ķä¸Ģ个
    0.26
     Instruction
    0.25
    訪
    0.24
    ongs
    0.24
    ä½ĥ
    0.24
    ä¸Ģ缴å¤Ħäºİ
    0.24
    é£İ鼨
    0.24
    Activations Density 14.236%

    No Known Activations

    This feature has no known activations.