© 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. 19-TRANSCODER-HP
    7. 8373
    Prev
    Next
    INDEX
    Explanations

    citations, numerical computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĵĦ
    -0.28
    inces
    -0.28
     ngo
    -0.27
    çļĦæ°Ķæģ¯
    -0.25
    ateur
    -0.25
    assin
    -0.24
    ingly
    -0.24
     cls
    -0.24
    itat
    -0.24
    iswa
    -0.23
    POSITIVE LOGITS
    å¤Ħ
    0.27
    æĢĢ
    0.26
    稳
    0.25
    äm
    0.24
     Acres
    0.24
    ız
    0.24
     outnumber
    0.24
    alendar
    0.24
    sim
    0.24
    ë©Ģ
    0.24
    Activations Density 0.012%

    No Known Activations