© 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. 141000
    Prev
    Next
    INDEX
    Explanations

    research 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
    cert
    -0.27
    bare
    -0.27
    éĤ£ä¸Ģ
    -0.25
    isper
    -0.25
    spiracy
    -0.24
    ä¸Ģåı£
    -0.23
     Lin
    -0.23
     osp
    -0.23
    ä»ģ
    -0.23
    /Foundation
    -0.23
    POSITIVE LOGITS
    illage
    0.32
    女ãģ®
    0.26
    ilha
    0.25
    墨西åĵ¥
    0.25
     unge
    0.25
    Raised
    0.24
    æĥħåĨµè¿Ľè¡Į
    0.24
    åĢĻéĢī
    0.24
    iage
    0.24
    è¿Ļä¹Īåģļ
    0.24
    Activations Density 16.157%

    No Known Activations