© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6218
    Prev
    Next
    INDEX
    Explanations

    sensitive

    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
    quiv
    -0.31
    izont
    -0.24
     Courier
    -0.23
    lings
    -0.23
    erg
    -0.23
     Formatter
    -0.23
    便
    -0.22
    oving
    -0.22
    helpers
    -0.22
    使æĪij
    -0.21
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.25
    cratch
    0.25
    /private
    0.24
     deprivation
    0.24
    åľ¨è¿Ļæĸ¹éĿ¢
    0.23
    ance
    0.23
     khu
    0.23
     kepada
    0.22
     grooming
    0.22
    ctp
    0.22
    Activations Density 1.607%

    No Known Activations