© 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. 129952
    Prev
    Next
    INDEX
    Explanations

    wasn

    np_max-act · gemini-2.0-flash
    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
    ä¸įç¦ģ
    -0.25
    ä¸įå¼Ģ
    -0.25
     Craw
    -0.25
    athi
    -0.25
    èµłéĢģ
    -0.24
    weep
    -0.24
    wij
    -0.24
    -hook
    -0.24
    æľ¬äºº
    -0.24
     survives
    -0.24
    POSITIVE LOGITS
    课æĸĩ
    0.29
    åIJĮ缣
    0.26
    åıį转
    0.26
    æ´ĭèij±
    0.26
    æŀģ
    0.25
     classmates
    0.25
    è¯¾æľ¬
    0.25
    åħ³éĶ®åŃĹ
    0.25
     shoes
    0.25
     logical
    0.25
    Activations Density 64.529%

    No Known Activations