© 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. 130771
    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
    æ·¡
    -0.33
    ëĵľë¦¬
    -0.27
    }))
    -0.25
     momento
    -0.24
    }|
    -0.24
    kiem
    -0.24
    analy
    -0.23
     Anal
    -0.23
    人们
    -0.23
     Kirk
    -0.23
    POSITIVE LOGITS
    åħ·å¤ĩ
    0.29
    æľīæľºä¼ļ
    0.26
    usions
    0.26
    acher
    0.26
    åij¼
    0.26
    lasses
    0.26
    çĪ±ä½ł
    0.26
    èĥ½è¾¾åĪ°
    0.26
    à¸Ĺราà¸ļ
    0.25
    uring
    0.25
    Activations Density 33.679%

    No Known Activations

    This feature has no known activations.