© 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. 63936
    Prev
    Next
    INDEX
    Explanations

    locations and institutions

    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
    修为
    -0.28
    ä¿¡æģ¯æľįåĬ¡
    -0.26
    ours
    -0.26
    icit
    -0.26
    atin
    -0.26
    DetailsService
    -0.26
    èĥ½åĬĽåĴĮ
    -0.25
    itial
    -0.23
    åĽłæŀľ
    -0.23
    å®ŀçĶ¨
    -0.23
    POSITIVE LOGITS
     withStyles
    0.27
    æģŃåĸľ
    0.26
     Worlds
    0.26
    ä¸ĢæĶ¯
    0.25
    paces
    0.25
     Roberts
    0.25
    UDO
    0.24
     flatten
    0.24
    ARAM
    0.24
    ä¸Ģåıª
    0.24
    Activations Density 5.632%

    No Known Activations