© 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. 22-TRANSCODER-HP
    7. 112060
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -owned
    -0.28
    åĴ¸
    -0.27
    ÑĢей
    -0.27
    ниÑĨа
    -0.27
    æĭ¥
    -0.26
    æľª
    -0.26
    笳
    -0.26
    è°¥
    -0.26
    earch
    -0.25
     closet
    -0.25
    POSITIVE LOGITS
    款
    0.29
    vern
    0.28
     resources
    0.27
    对åħ¶è¿Ľè¡Į
    0.26
     qued
    0.25
    ized
    0.25
    .getExternal
    0.24
    åĮĸçļĦ
    0.24
    ãģĹãģ¦ãģĬãģı
    0.24
    èµĦæºIJ
    0.24
    Activations Density 0.006%

    No Known Activations