© 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. 129568
    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
     stores
    -0.27
    åħ´è¶£
    -0.26
    tere
    -0.25
    Ø·
    -0.25
     Presence
    -0.25
    ä»·åĢ¼éĵ¾
    -0.24
    éģĩéļ¾
    -0.24
    (store
    -0.24
    âį¨
    -0.24
    averse
    -0.24
    POSITIVE LOGITS
    ammer
    0.29
    就好äºĨ
    0.26
    éĥ½ä¸įèĥ½
    0.25
    æĺ§
    0.24
     stacking
    0.24
    å°±åı¯ä»¥äºĨ
    0.24
    ãģĹãģŁãĤī
    0.23
    åħļæĢ»æĶ¯
    0.23
    åĥı个
    0.23
    erton
    0.23
    Activations Density 2.542%

    No Known Activations

    This feature has no known activations.