© 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. 19-TRANSCODER-HP
    7. 4727
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    æĿĤ
    -0.27
    åģĥ
    -0.27
    åİĺ
    -0.26
    ç²Ĵ
    -0.26
     none
    -0.25
    aki
    -0.25
    ä¸ĢåĽ¢
    -0.25
    _none
    -0.25
    åĪĨå¸ĥ
    -0.24
    .none
    -0.23
    POSITIVE LOGITS
    olicit
    0.28
    orable
    0.26
     shortened
    0.26
    ighbors
    0.25
    FTER
    0.24
    举æĬ¥
    0.24
    éļª
    0.24
    orage
    0.24
    ä¹ĭåIJİ
    0.23
    FFE
    0.23
    Activations Density 0.013%

    No Known Activations