© 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. 87192
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
    çŃ¾ç½²äºĨ
    -0.29
    ä¸īæĿ¡
    -0.27
    dem
    -0.26
     TOOL
    -0.25
    å°ıé¢Ŀ
    -0.25
     Courtesy
    -0.24
    __$
    -0.24
     Specialty
    -0.24
    æĹ¶æľŁçļĦ
    -0.23
    åĩłåIJį
    -0.23
    POSITIVE LOGITS
     blue
    0.28
    æĢģ
    0.28
    (ins
    0.28
    OMPI
    0.27
    omite
    0.27
    ắng
    0.27
    ays
    0.26
    kt
    0.26
    oins
    0.25
    IDS
    0.25
    Activations Density 0.031%

    No Known Activations