© 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. 129919
    Prev
    Next
    INDEX
    Explanations

    objectives

    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
    æıĴ
    -0.28
    ipples
    -0.28
    kits
    -0.26
    fra
    -0.26
    sher
    -0.25
     med
    -0.25
    udo
    -0.25
     solutions
    -0.24
    ica
    -0.24
     Solutions
    -0.24
    POSITIVE LOGITS
     fluent
    0.29
     skyline
    0.27
    åĩĢ
    0.26
    ä¿Ŀè¯ģ
    0.25
    );;↵
    0.25
    (fil
    0.24
    ä¸ĩ象
    0.24
    åĩĢèµĦ产
    0.24
    inline
    0.23
    loses
    0.23
    Activations Density 0.003%

    No Known Activations