© 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. 108563
    Prev
    Next
    INDEX
    Explanations

    Academic/technical writing

    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
    Negative Logits
    ------↵
    -0.29
     lied
    -0.28
    uba
    -0.27
    åľŁè±ª
    -0.26
    -global
    -0.26
    -edge
    -0.25
    èŀį
    -0.25
    é¡¿
    -0.25
    å±ĬæŶ
    -0.24
    legacy
    -0.24
    POSITIVE LOGITS
     insecurity
    0.27
    ä¸Ģåıªæīĭ
    0.25
     пÑĢеп
    0.24
    åı¯èĥ½åıijçĶŁ
    0.24
    amble
    0.24
    æĿŁ
    0.24
     hay
    0.23
    inent
    0.23
    â¨
    0.23
    arrants
    0.23
    Activations Density 58.301%

    No Known Activations