© 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. 130012
    Prev
    Next
    INDEX
    Explanations

    agriculture

    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
     crow
    -0.28
    rita
    -0.28
    æłĩ
    -0.28
     flex
    -0.27
     lot
    -0.27
    exercise
    -0.26
    请éĢīæĭ©
    -0.25
     Exercise
    -0.25
    ç¡®å®ļ
    -0.25
    ä¼ļéķ¿
    -0.25
    POSITIVE LOGITS
    orphic
    0.28
    åľ°ä¸Ń
    0.26
     addCriterion
    0.26
     productService
    0.25
     ProductService
    0.25
    产åĵģè´¨éĩı
    0.25
    ief
    0.24
    born
    0.24
    oped
    0.24
    æĭ¿çĿĢ
    0.23
    Activations Density 0.006%

    No Known Activations