© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 67
    Prev
    Next
    INDEX
    Explanations

    compat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hiba
    -0.29
    ç»Ļ她
    -0.28
    ç»ĻæĤ¨
    -0.27
    ç»ĻåŃ©åŃIJ
    -0.26
    éĸ£
    -0.26
    她说
    -0.25
    kas
    -0.25
    æ±Ń
    -0.24
    chy
    -0.24
    kö
    -0.24
    POSITIVE LOGITS
    åįĩåѦ
    0.26
     el
    0.25
     spotlight
    0.25
    å©ļ
    0.25
    éģij
    0.25
    Dan
    0.24
    cken
    0.24
    æŀľ
    0.24
    Cor
    0.24
     pl
    0.24
    Activations Density 0.009%

    No Known Activations