© 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. 130011
    Prev
    Next
    INDEX
    Explanations

    Scientific studies

    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
    ={({
    -0.26
    Hidden
    -0.25
    ä¸Ģç¢Ĺ
    -0.24
     chặt
    -0.24
     orbs
    -0.23
    严å¯Ĩ
    -0.23
    ModifiedDate
    -0.23
     Rahul
    -0.23
     /*----------------------------------------------------------------
    -0.23
    arbon
    -0.23
    POSITIVE LOGITS
    ä¸ĵ
    0.28
    身
    0.28
     spit
    0.26
    æ·Ģ
    0.25
    itemap
    0.24
    æŃ¥è¡Į
    0.24
     Yap
    0.24
    ä»Ģä¹Īä¸ľè¥¿
    0.24
    iação
    0.23
     unfortunately
    0.23
    Activations Density 8.381%

    No Known Activations