© 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. 9095
    Prev
    Next
    INDEX
    Explanations

    Web-scraped data

    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
    èļ¤
    -0.28
    porto
    -0.26
    entes
    -0.26
    ä¼´éļıçĿĢ
    -0.25
    )>>
    -0.25
    éĴ¿
    -0.25
    uat
    -0.25
    âĢ¦)
    -0.25
    WARE
    -0.25
    wat
    -0.25
    POSITIVE LOGITS
    åĬ±å¿Ĺ
    0.28
    ambi
    0.27
     major
    0.26
     thereafter
    0.26
    ibr
    0.26
    ascript
    0.26
    计
    0.26
     Major
    0.26
    ardi
    0.25
    arded
    0.25
    Activations Density 0.006%

    No Known Activations