© 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. 63270
    Prev
    Next
    INDEX
    Explanations

    Scientific and academic 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
    ç¡IJ
    -0.25
    eten
    -0.25
    æĹłè¾ľ
    -0.24
    orro
    -0.24
    igar
    -0.24
    ä¸Ģ个å¤ļ
    -0.24
    ãĤĤãģĹ
    -0.24
    仫
    -0.24
    egal
    -0.24
     оÑĤз
    -0.23
    POSITIVE LOGITS
    å®ŀè´¨
    0.29
     embedding
    0.28
    å¾Ħ
    0.27
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.26
     regular
    0.26
    贯穿
    0.25
     ÐŁÐµÑĢе
    0.25
    管çIJĨåijĺ
    0.25
    obia
    0.25
    Ty
    0.25
    Activations Density 32.067%

    No Known Activations