© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7548
    Prev
    Next
    INDEX
    Explanations

    Initials and names

    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
    èĬ®
    -0.26
    jah
    -0.26
    itions
    -0.26
    ãģĹãģ¾
    -0.25
    rial
    -0.25
    è¾ĸ
    -0.25
    失
    -0.24
     forg
    -0.24
    sono
    -0.24
    èĴĻåı¤
    -0.24
    POSITIVE LOGITS
    анÑģ
    0.25
    ivre
    0.25
    大ä¼ļ
    0.24
     imp
    0.24
     treeNode
    0.24
     GlobalKey
    0.23
    æ¡Īä¾ĭ
    0.23
    çļĦæĥħåĨµ
    0.23
    unnel
    0.22
    auf
    0.22
    Activations Density 0.008%

    No Known Activations