© 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. 130339
    Prev
    Next
    INDEX
    Explanations

    light and illumination

    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
    ÑģÑĤеÑĢ
    -0.28
     chá
    -0.25
    åĮĸçļĦ
    -0.25
    æµĬ
    -0.24
     jd
    -0.24
    å¹´ä¹ĭ
    -0.24
    /entities
    -0.23
    竽
    -0.23
    jom
    -0.23
    ç»ıèIJ¥ç®¡çIJĨ
    -0.23
    POSITIVE LOGITS
     elimin
    0.27
    YG
    0.26
     Architect
    0.26
     suppl
    0.26
    earth
    0.25
     earth
    0.24
     Elim
    0.24
    à¹īà¸ĩ
    0.24
     eye
    0.23
    osten
    0.23
    Activations Density 0.005%

    No Known Activations