© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 106860
    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
    Negative Logits
    sonian
    -0.27
    /root
    -0.26
    ç´§æİ¥çĿĢ
    -0.25
    æľºæ²¹
    -0.25
    欢
    -0.25
    okit
    -0.25
    è¯ķè¯ķ
    -0.25
     Rif
    -0.25
    ä½ĵæ£Ģ
    -0.24
    åīįåı°
    -0.24
    POSITIVE LOGITS
    èĥ½å¤ł
    0.26
    åIJį称
    0.26
    Difficulty
    0.24
    -Ta
    0.23
    nothing
    0.23
     difficulty
    0.23
    èĥ½å¤Ł
    0.23
     ÃĤu
    0.23
    åĢķ
    0.23
    å§ĵåIJį
    0.23
    Activations Density 0.208%

    No Known Activations

    This feature has no known activations.