© 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. 130351
    Prev
    Next
    INDEX
    Explanations

    Choices or alternatives

    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
     everything
    -0.28
    acia
    -0.28
    é½IJ
    -0.27
    bfd
    -0.26
    æ´Ĺå¹²åĩĢ
    -0.26
     consistency
    -0.25
    åħ¼é¡¾
    -0.25
    æĶ¶éĽĨ
    -0.24
    ancel
    -0.24
    æ´ĹåĩĢ
    -0.24
    POSITIVE LOGITS
    æŁIJ个
    0.40
    æĪĸåħ¶ä»ĸ
    0.39
    æĪĸæĺ¯
    0.38
    æĪĸ
    0.38
    æĪĸèĢħ
    0.37
     æĪĸ
    0.35
     eller
    0.35
    æĪĸèĢħåħ¶ä»ĸ
    0.35
    æĪĸèĢħæĺ¯
    0.35
     algun
    0.35
    Activations Density 45.206%

    No Known Activations