© 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. 24-TRANSCODER-HP
    7. 150245
    Prev
    Next
    INDEX
    Explanations

    approximations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocomplete
    -0.26
    quist
    -0.26
    iek
    -0.24
    kart
    -0.24
    allest
    -0.24
    etrain
    -0.24
    jes
    -0.23
    åIJĪä¼Ļ
    -0.23
     fav
    -0.23
     ÑģоÑħÑĢани
    -0.23
    POSITIVE LOGITS
    æķ´ä¸ªäºº
    0.29
    ä¸ĩ人
    0.28
    adas
    0.28
    ä¸įå°ij人
    0.26
     repr
    0.26
    æ¤Ĵ
    0.24
    åħ¬çĶ¨
    0.23
    æݨ广åºĶçĶ¨
    0.23
     Braz
    0.23
    çĻ¾
    0.23
    Activations Density 0.116%

    No Known Activations