© 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. 63112
    Prev
    Next
    INDEX
    Explanations

    Technical/regulatory texts

    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
    alte
    -0.30
    emet
    -0.28
     halves
    -0.26
    æ´¾
    -0.26
    jos
    -0.26
    é«ĺä½İ
    -0.26
    çĴ§
    -0.25
    çĻ»
    -0.25
    ä»ij
    -0.25
    祼
    -0.25
    POSITIVE LOGITS
    åIJĮæľŁ
    0.31
    éĴĪ
    0.26
    ä¹Łæĺ¯ä¸Ģç§į
    0.26
    FIELD
    0.26
     transparent
    0.25
    åįıåĬŀ
    0.25
    éĩĿ
    0.25
    åIJĮæĻĤ
    0.24
    hest
    0.24
    à¹Īว
    0.24
    Activations Density 4.645%

    No Known Activations