© 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. 107773
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     setC
    -0.29
     yourselves
    -0.28
    ç¡®ç«ĭ
    -0.28
    PLICATE
    -0.26
    åĴ¸
    -0.25
    ä½ĵçİ°äºĨ
    -0.25
     Traverse
    -0.25
    æ¿ķ
    -0.24
    opened
    -0.24
    åĪĽå§ĭ
    -0.24
    POSITIVE LOGITS
    rÃŃ
    0.28
    å½Ģ
    0.27
    强度
    0.25
    åľ£åľ°
    0.24
    æ»ļåĬ¨
    0.24
    pei
    0.24
    år
    0.24
    诳
    0.23
    acula
    0.23
    wang
    0.23
    Activations Density 11.380%

    No Known Activations