© 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. 142147
    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
    WithValue
    -0.31
    æīĵæĸŃ
    -0.27
    ä¹ĺ
    -0.26
    ods
    -0.26
    çݯçIJĥ
    -0.24
    å¼łå®¶
    -0.24
    éĿŀ常åĸľæ¬¢
    -0.24
    Ñįн
    -0.24
     enth
    -0.24
    Loop
    -0.24
    POSITIVE LOGITS
     lá»ĩ
    0.28
    嬷
    0.27
    uzzi
    0.26
     cud
    0.25
    IVAL
    0.24
    ä¿Ŀ湿
    0.24
    ailles
    0.24
    éĤ£ä»½
    0.23
     wz
    0.23
    PEED
    0.23
    Activations Density 22.870%

    No Known Activations

    This feature has no known activations.