© 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. 19-TRANSCODER-HP
    7. 9012
    Prev
    Next
    INDEX
    Explanations

    External

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Happy
    -0.27
     instantaneous
    -0.26
    身
    -0.26
    æŀģ
    -0.25
    ins
    -0.25
    á»Ļc
    -0.25
     %%↵
    -0.24
    大ä¼Ĺ
    -0.24
    iva
    -0.24
     kans
    -0.23
    POSITIVE LOGITS
    mland
    0.29
    æĮĩåįĹ
    0.27
    aille
    0.27
    è¹Ĵ
    0.26
     amacıyla
    0.26
    å¿łå®ŀ
    0.26
    THON
    0.26
    ä¼´éļı
    0.25
     somew
    0.25
    _foot
    0.24
    Activations Density 0.008%

    No Known Activations